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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 27832
    Prev
    Next
    INDEX
    Explanations

    revealed

    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
     преимуществ
    -0.07
    ペット
    -0.06
     SAT
    -0.06
    סדר
    -0.06
    .ms
    -0.06
     coordinator
    -0.06
    PED
    -0.06
    mö
    -0.06
    נסה
    -0.06
    办法
    -0.06
    POSITIVE LOGITS
    💌
    0.07
    悦
    0.06
    PEAT
    0.06
    ooting
    0.06
    看向
    0.06
    riteln
    0.06
    (socket
    0.06
    😜
    0.06
    inoa
    0.06
    五百
    0.06
    Activations Density 0.179%

    No Known Activations