© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 77357
    Prev
    Next
    INDEX
    Explanations

    the neuron detects technical documentation and code-comment language — formal, informational tokens that appear in software docs, headers, or descriptions of metrics/indicators.

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -0.09
     OF
    -0.08
    养生
    -0.08
    _PUSH
    -0.08
    七
    -0.08
    ŗ
    -0.08
    uç
    -0.08
    资源配置
    -0.07
    addtogroup
    -0.07
    迁移
    -0.07
    POSITIVE LOGITS
     is
    0.17
     was
    0.11
     are
    0.10
     isSelected
    0.08
     ist
    0.08
    /is
    0.08
     deut
    0.07
    .is
    0.07
     لأنه
    0.07
     headphones
    0.07
    Activations Density 2.062%

    No Known Activations