© 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. 32706
    Prev
    Next
    INDEX
    Explanations

    listing items and abbreviations

    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
    认å®ļ
    -0.09
    ério
    -0.08
    认
    -0.08
    .cz
    -0.08
    åħĪæĺ¯
    -0.08
    коÑģ
    -0.08
     ERA
    -0.08
    AMP
    -0.08
    è¿ĺ
    -0.08
    åĴĮ社ä¼ļ
    -0.08
    POSITIVE LOGITS
     etc
    0.32
    çŃīçŃī
    0.26
    etc
    0.26
    çŃīæĥħåĨµ
    0.21
    ãģªãģ©
    0.20
    çŃīé¢ĨåŁŁ
    0.19
    çŃīæĸ¹éĿ¢
    0.18
    çŃīéĹ®é¢ĺ
    0.17
    çŃīåIJĦç§į
    0.17
    çŃīçī¹çĤ¹
    0.17
    Activations Density 0.197%

    No Known Activations