© 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. 36511
    Prev
    Next
    INDEX
    Explanations

    long-term | coherence | efficiency | Growth

    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
    书ç±į
    -0.09
    éĢĢåĩº
    -0.09
    请大家
    -0.09
    çĿĢçľ¼
    -0.09
     Exit
    -0.08
    ãģ¶
    -0.08
    éĵĥ
    -0.08
    åľ£
    -0.08
    cobra
    -0.08
    æľĢå¿«
    -0.08
    POSITIVE LOGITS
    wt
    0.10
    åīĶ
    0.09
    _dummy
    0.08
    IndexOf
    0.08
    åįľ
    0.08
    çĶļèĩ³æĺ¯
    0.08
    WT
    0.08
    污æŁĵ
    0.08
     accommod
    0.07
     contest
    0.07
    Activations Density 0.108%

    No Known Activations