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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 89839
    Prev
    Next
    INDEX
    Explanations

    alternatives and options

    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
    笫
    -0.08
    Throws
    -0.07
    ’.↵↵
    -0.07
    kö
    -0.06
    Nine
    -0.06
     veterinarian
    -0.06
    Provid
    -0.06
     Vet
    -0.06
    達到
    -0.06
    Roman
    -0.06
    POSITIVE LOGITS
    -heavy
    0.08
     عليها
    0.08
    救护
    0.07
     عليهم
    0.07
     hysteria
    0.07
     ابو
    0.07
    améli
    0.07
    ❆
    0.07
     yPos
    0.06
    に入る
    0.06
    Activations Density 0.091%

    No Known Activations