© 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. 8510
    Prev
    Next
    INDEX
    Explanations

    important information or concept

    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
    sr
    -0.11
    åħ·ä½ĵåĨħ容
    -0.10
    æ¶Ī
    -0.09
    大åĨĽ
    -0.09
    大æĸ¹
    -0.09
    оÑģÑĤей
    -0.09
     OPTIONAL
    -0.08
     Farrell
    -0.08
    åĽ°å¢ĥ
    -0.08
    tps
    -0.08
    POSITIVE LOGITS
    ç»ĦæĪIJéĥ¨åĪĨ
    0.11
    åĩłæŃ¥
    0.10
    æ°ijçĶŁ
    0.09
    /use
    0.09
    ä»Ķ
    0.09
    éĿ¢åŃIJ
    0.09
    强è°ĥ
    0.09
    éĿŀ常éĩįè¦ģ
    0.09
     vital
    0.09
    å·½
    0.09
    Activations Density 0.218%

    No Known Activations