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. 11-RESID-POST-AA
    6. 22991
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cong
    -0.07
     Conf
    -0.07
     Storm
    -0.07
    Post
    -0.07
     rest
    -0.07
    悄
    -0.07
     Consort
    -0.06
     forecast
    -0.06
     ASD
    -0.06
    -Ass
    -0.06
    POSITIVE LOGITS
    *****
    ↵
    0.08
    なぜ
    0.07
    โคร
    0.07
    '];
    ↵
    0.07
    تحق
    0.07
    דרג
    0.07
     Heroes
    0.07
    튤
    0.07
    まさ
    0.07
     eerste
    0.07
    Activations Density 0.011%

    No Known Activations