© 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. 30357
    Prev
    Next
    INDEX
    Explanations

    based on

    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
    大éĥ¨åĪĨ
    -0.10
    æĴij
    -0.10
    æ±
    -0.09
     Stevens
    -0.09
    æµ·æ£ł
    -0.09
    onders
    -0.09
    åĪ¹
    -0.09
    itat
    -0.09
    /forms
    -0.08
    aze
    -0.08
    POSITIVE LOGITS
    æľĢæĸ°çļĦ
    0.10
    åĨħç½®
    0.10
    _UPDATED
    0.09
    å®ŀéĻħæĥħåĨµ
    0.09
    å¸ĤåľºéľĢæ±Ĥ
    0.08
    æīĢæıIJä¾ĽçļĦ
    0.08
    £¼
    0.08
    客æĪ·éľĢæ±Ĥ
    0.08
    éĩĮç¨ĭç¢ij
    0.08
     based
    0.08
    Activations Density 0.078%

    No Known Activations