© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 76005
    Prev
    Next
    INDEX
    Explanations

    User interaction prompts

    np_max-act · gemini-2.0-flash

    the neuron detects conversation boundary tokens/assistant message end markers (tokens that mark the end of a turn or end-of-message).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expenditure
    -0.08
    /sign
    -0.07
    elling
    -0.07
    RequestMapping
    -0.07
     temptation
    -0.07
    销售收入
    -0.07
     shores
    -0.07
    報告
    -0.07
    可以看到
    -0.07
    实际情况
    -0.07
    POSITIVE LOGITS
    гер
    0.07
    מבוגרים
    0.07
    汭
    0.07
     Charset
    0.06
     happy
    0.06
    合い
    0.06
    ਰ
    0.06
    med
    0.06
    Spell
    0.06
    ром
    0.06
    Activations Density 0.159%

    No Known Activations