© 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. 6608
    Prev
    Next
    INDEX
    Explanations

    win and giveaways

    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
    olean
    -0.10
    趸
    -0.08
    InChildren
    -0.08
    è¹Ĭ
    -0.08
    éĻ²
    -0.08
    央
    -0.08
    inha
    -0.08
    éĢ¢
    -0.08
    ductive
    -0.08
    ather
    -0.08
    POSITIVE LOGITS
    /AP
    0.10
    禽
    0.09
     Åļ
    0.08
    mirror
    0.08
    _Utils
    0.08
    stitial
    0.08
    Daily
    0.08
    scar
    0.08
    éľĩ
    0.08
    endi
    0.08
    Activations Density 0.010%

    No Known Activations