© 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. 37554
    Prev
    Next
    INDEX
    Explanations

    license copyright ownership

    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
     lik
    -0.09
    egan
    -0.09
    LIK
    -0.08
    urg
    -0.08
    亲åŃIJ
    -0.08
    opor
    -0.08
    é«ĺçŃī
    -0.08
    å¾Īå¤ļäºĭæĥħ
    -0.08
    åľ¨äº¬
    -0.08
    .ObjectModel
    -0.08
    POSITIVE LOGITS
    å¹£
    0.10
    ç»Į
    0.09
    .tables
    0.09
    æİĪ课
    0.09
    ç¾İ容
    0.09
    å¾Ĺä¸įåĪ°
    0.09
    {text
    0.09
    .Ui
    0.08
    cord
    0.08
    atat
    0.08
    Activations Density 0.011%

    No Known Activations