© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6819
    Prev
    Next
    INDEX
    Explanations

    team up with

    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
    curity
    -0.09
    çľĭä»ĸ
    -0.09
    urat
    -0.08
    æĬ¹
    -0.08
    ä¸į说
    -0.08
    parator
    -0.08
    yat
    -0.08
    (OP
    -0.08
    gli
    -0.08
    üns
    -0.08
    POSITIVE LOGITS
    è¡ĮåĬ¨
    0.09
    åĢľ
    0.09
    帽åŃIJ
    0.09
    æŃ¡
    0.08
    è¡«
    0.08
    åĽ½æĥħ
    0.08
    æĶ»åħĭ
    0.08
    åĽ½éĻħåIJĪä½ľ
    0.08
    éľ¹
    0.08
    кÑĥп
    0.08
    Activations Density 0.003%

    No Known Activations