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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 43960
    Prev
    Next
    INDEX
    Explanations

    Copyright

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🌆
    -0.07
    יח
    -0.06
    죵
    -0.06
     tố
    -0.06
     Byron
    -0.06
     Thief
    -0.06
    ig
    -0.06
    ዩ
    -0.06
     smb
    -0.06
     Beyond
    -0.06
    POSITIVE LOGITS
    wróci
    0.07
     Runs
    0.07
    _whitespace
    0.07
    大幅度
    0.07
     generously
    0.06
     clearance
    0.06
     результат
    0.06
    "]↵
    0.06
    的大
    0.06
    ائها
    0.06
    Activations Density 0.028%

    No Known Activations