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. 87073
    Prev
    Next
    INDEX
    Explanations

    biographical passages

    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
    的空间
    -0.07
    𝘈
    -0.07
     הספר
    -0.07
     rallies
    -0.06
    焉
    -0.06
     _____
    -0.06
    基金份额
    -0.06
    [args
    -0.06
    .strftime
    -0.06
     drawers
    -0.06
    POSITIVE LOGITS
     indicating
    0.08
    .cod
    0.08
                ↵
    0.07
     withd
    0.07
     reaching
    0.07
    mock
    0.07
            
    ↵
    0.07
     bounding
    0.06
     diving
    0.06
     human
    0.06
    Activations Density 0.455%

    No Known Activations