© 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. 38310
    Prev
    Next
    INDEX
    Explanations

    hang out

    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
    kers
    -0.10
    æĹģ
    -0.10
    _NT
    -0.09
    å½»
    -0.09
    éĻĩ
    -0.09
    idents
    -0.09
    éĥ
    -0.08
    obuf
    -0.08
    ä¸īç§į
    -0.08
     détail
    -0.08
    POSITIVE LOGITS
    åĪij
    0.09
    å¢Ļ
    0.09
    zone
    0.09
    åĪ¶å®ļäºĨ
    0.09
    ç½®
    0.08
    åľ¨åŃ¦æł¡
    0.08
     snag
    0.08
    aug
    0.08
    ster
    0.08
    åľ¨åĮĹ京
    0.08
    Activations Density 0.007%

    No Known Activations