© 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. 58368
    Prev
    Next
    INDEX
    Explanations

    problem is that

    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
     Forced
    -0.08
    åĺĺ
    -0.08
     ale
    -0.08
    è¾ľè´Ł
    -0.08
    计
    -0.08
    ä¸į符
    -0.08
     Mane
    -0.08
    åIJĮæĥħ
    -0.08
    ç«ł
    -0.08
    æ¦Ħ
    -0.08
    POSITIVE LOGITS
    ä¾ĿçĦ¶
    0.42
    ä¾Ŀæŧ
    0.38
    ä»įçĦ¶
    0.36
    ä»į
    0.33
    ä»įæľī
    0.32
    ä¾ĿçĦ¶æĺ¯
    0.32
    继ç»Ń
    0.32
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.31
    ä»įåľ¨
    0.31
    ä»įæŧ
    0.31
    Activations Density 0.167%

    No Known Activations