© 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. 22591
    Prev
    Next
    INDEX
    Explanations

    asked someone

    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
    éĢĤåIJĪèĩªå·±
    -0.10
    å¿įåıĹ
    -0.09
    wahl
    -0.09
    ä¸įå¿į
    -0.09
    以便
    -0.09
    å¹½é»ĺ
    -0.09
    .fromJson
    -0.09
    SimpleName
    -0.08
    å¸ĮæľĽèĥ½
    -0.08
    è¿«
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķä¸Ģ个
    0.11
    éĥ½ä¼ļ
    0.11
    说åĩº
    0.10
    å°±ç®Ĺ
    0.10
    ä¼ļè®©ä½ł
    0.10
    ä»ĸä¼ļ
    0.09
    ä»ĸ们ä¼ļ
    0.09
    éĴŀ
    0.09
     Likely
    0.09
    ä½łä¼ļ
    0.09
    Activations Density 0.067%

    No Known Activations