Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10997
    Prev
    Next
    INDEX
    Explanations

    bee

    np_max-act · gemini-2.0-flash
    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
     Golf
    -0.08
     sol
    -0.07
     garn
    -0.07
     Trou
    -0.07
    _BEGIN
    -0.07
    dling
    -0.07
     tackle
    -0.07
     troubled
    -0.07
    <boolean
    -0.07
    ARENT
    -0.06
    POSITIVE LOGITS
     bees
    0.08
    แพง
    0.07
    雷锋
    0.07
     nearby
    0.07
    kbd
    0.07
     המכ
    0.07
    均
    0.06
    +b
    0.06
     прос
    0.06
    MQ
    0.06
    Activations Density 0.005%

    No Known Activations