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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 78238
    Prev
    Next
    INDEX
    Explanations

    This neuron detects tokens that express providing or requesting assistance or help (mentions of helping, assistance, or offers to help).

    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
     isActive
    -0.08
     düşün
    -0.07
    andez
    -0.07
    character
    -0.07
    在上海
    -0.07
    (Vector
    -0.07
     Champagne
    -0.07
     ){
    -0.07
    但仍
    -0.06
    昨天
    -0.06
    POSITIVE LOGITS
     the
    0.08
     multitude
    0.08
    쒸
    0.07
     racial
    0.07
    힛
    0.07
     The
    0.07
    pción
    0.07
     إليه
    0.07
    妙
    0.07
     מהם
    0.07
    Activations Density 0.240%

    No Known Activations