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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 78464
    Prev
    Next
    INDEX
    Explanations

    Holder

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.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
    身形
    -0.07
    𝚟
    -0.07
    	elsif
    -0.07
    HttpGet
    -0.06
    ᐢ
    -0.06
    >}</
    -0.06
    ()))
↵
    -0.06
     trực
    -0.06
    username
    -0.06
    POSITIVE LOGITS
    亭
    0.07
    祖父
    0.07
    mandatory
    0.07
     ylabel
    0.07
     arty
    0.07
     prove
    0.07
    穿着
    0.07
    污泥
    0.07
    /ts
    0.07
    (Material
    0.07
    Activations Density 0.005%

    No Known Activations