© 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. 21584
    Prev
    Next
    INDEX
    Explanations

    legal or code contexts

    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
    ä»İæĿ¥ä¸į
    -0.09
    3
    -0.08
    4
    -0.08
    annes
    -0.08
    6
    -0.08
    æį£
    -0.08
    éªĮ
    -0.08
     anv
    -0.08
    9
    -0.08
    ç»Īæŀģ
    -0.07
    POSITIVE LOGITS
    èIJ½
    0.10
    书记
    0.09
    çīĩåĪ»
    0.08
    _fragment
    0.08
    inous
    0.08
    (.)
    0.08
    istani
    0.07
    ãģĶåĪ©çĶ¨
    0.07
    åħļé£İ
    0.07
     <![
    0.07
    Activations Density 0.242%

    No Known Activations