© 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. 53255
    Prev
    Next
    INDEX
    Explanations

    names

    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
    igos
    -0.10
    esk
    -0.09
    æĬ«
    -0.09
    æ»Ĥ
    -0.09
    ÑĦоÑĢ
    -0.09
    建åĨĽ
    -0.09
    æĥ³æĥ³
    -0.09
    <Real
    -0.08
     Beverage
    -0.08
    éĻĢ
    -0.08
    POSITIVE LOGITS
    æĹłè®ºå¦Ĥä½ķ
    0.10
    ä¸Ģ人
    0.09
    éĢĬ
    0.09
    fila
    0.08
    åī²
    0.08
    вел
    0.08
    马路
    0.08
    达人
    0.08
    æį¢
    0.08
    顯
    0.08
    Activations Density 0.141%

    No Known Activations