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. 115255
    Prev
    Next
    INDEX
    Explanations

    :

    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
    読み
    -0.08
    .bean
    -0.08
    .prev
    -0.07
     ken
    -0.07
    .kwargs
    -0.06
    中心主任
    -0.06
    ဖ
    -0.06
     thư
    -0.06
    .Arg
    -0.06
    正因为
    -0.06
    POSITIVE LOGITS
    _format
    0.09
    꿔
    0.07
     Fiona
    0.07
     có
    0.06
    _chain
    0.06
     café
    0.06
     dục
    0.06
     deceptive
    0.06
     murder
    0.06
     when
    0.06
    Activations Density 0.034%

    No Known Activations