© 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. 15-RESID-POST-AA
    11. 48516
    Prev
    Next
    INDEX
    Explanations

    Choosing

    np_max-act · gemini-2.0-flash

    The neuron detects words and phrases that indicate choosing or selecting (selection/choice actions).

    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
    (get
    -0.08
    ำ
    -0.07
    Styled
    -0.07
    .shopping
    -0.07
    즌
    -0.07
    ный
    -0.07
     +"
    -0.07
    مراجعة
    -0.07
    azo
    -0.07
    _BASIC
    -0.07
    POSITIVE LOGITS
     cork
    0.06
     climbers
    0.06
     Circus
    0.06
     errorCallback
    0.06
     disturbing
    0.06
     selon
    0.06
    mıştır
    0.06
     Corpor
    0.06
    帽子
    0.06
    痛点
    0.06
    Activations Density 0.029%

    No Known Activations