© 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 EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 117722
    Prev
    Next
    INDEX
    Explanations

    decimal

    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
    <|im_start|>
    -0.07
    istream
    -0.07
    表演
    -0.07
    ảng
    -0.07
     min
    -0.07
     d
    -0.07
     ≥
    -0.07
     probability
    -0.07
    ล
    -0.07
    	buff
    -0.07
    POSITIVE LOGITS
    ordinary
    0.07
    (repository
    0.07
    一緒
    0.07
     modified
    0.07
    sterol
    0.07
     adres
    0.07
     Tasks
    0.06
    Redis
    0.06
     ecosystems
    0.06
     //!
    0.06
    Activations Density 0.001%

    No Known Activations