© 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. 57980
    Prev
    Next
    INDEX
    Explanations

    minimum, necessary, requirements

    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
    onda
    -0.09
    èĻ½çĦ¶
    -0.09
     Äijòi
    -0.09
    /off
    -0.08
    建åįİ
    -0.08
    æĽ´éĢĤåIJĪ
    -0.08
    ç¥ŀå·ŀ
    -0.08
    à´Ł
    -0.08
    åĩºåıij
    -0.08
    åIJijå¾Ģ
    -0.08
    POSITIVE LOGITS
    å¿ħè¦ģ
    0.17
    å¿ħè¦ģçļĦ
    0.17
     necessary
    0.14
     Necessary
    0.14
    necessary
    0.14
    å¿ħè¦ģãģª
    0.12
    ä¸įå¿ħè¦ģçļĦ
    0.11
     необÑħодим
    0.10
    å¿ħä¸įåı¯å°ij
    0.10
     necessity
    0.10
    Activations Density 0.084%

    No Known Activations