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. 14271
    Prev
    Next
    INDEX
    Explanations

    conversational, hedging

    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
     wybrać
    -0.07
    теля
    -0.07
     함
    -0.06
    Nam
    -0.06
     SAND
    -0.06
     Abort
    -0.06
    Six
    -0.06
     ################################################################
    -0.06
     ממ
    -0.06
     pil
    -0.06
    POSITIVE LOGITS
     scrollTop
    0.08
    🎂
    0.08
    徭
    0.07
    价值观
    0.07
    ulong
    0.07
     personne
    0.07
    "<<
    0.07
    PEnd
    0.07
    xfe
    0.07
    夬
    0.07
    Activations Density 0.282%

    No Known Activations