© 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. 11939
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    严
    -0.09
    åĴĮå¹³
    -0.08
     Lion
    -0.08
    alten
    -0.08
     Junior
    -0.08
     lt
    -0.08
    æľ¬åľŁ
    -0.08
    lion
    -0.08
    举æĸ¹
    -0.07
    éĺģ
    -0.07
    POSITIVE LOGITS
    ä¸Ģä¼ļ
    0.09
    å®ļå¾ĭ
    0.09
    igan
    0.09
    urname
    0.09
    allee
    0.09
    ç©°
    0.08
    é¢ĨæĤŁ
    0.08
     Curry
    0.08
    è§ij
    0.08
    å½
    0.08
    Activations Density 0.416%

    No Known Activations