© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33690
    Prev
    Next
    INDEX
    Explanations

    extension.plugins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    常å§Ķä¼ļ
    -0.10
    walk
    -0.10
    istic
    -0.09
    ç½®ä¸ļ
    -0.09
    تج
    -0.09
    .wrapper
    -0.09
    åħ¬ç¤¾
    -0.09
    HONE
    -0.08
    аÑĪ
    -0.08
    lier
    -0.08
    POSITIVE LOGITS
    /extensions
    0.10
    (extension
    0.10
    endar
    0.10
    remely
    0.09
    ordinary
    0.09
    延伸
    0.09
    reme
    0.09
     extension
    0.09
    chron
    0.08
    豸
    0.08
    Activations Density 0.052%

    No Known Activations