© 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. 48907
    Prev
    Next
    INDEX
    Explanations

    semi-

    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
    åij³
    -0.08
    à¹Ģà¸ķ
    -0.08
    çĭ¬è§Ĵ
    -0.08
    uhl
    -0.08
    å®ŀåľ¨
    -0.08
    ania
    -0.08
     Fulton
    -0.08
    rem
    -0.08
    ä¸įå®ī
    -0.08
    ä¸įå¾Ĺä¸į
    -0.08
    POSITIVE LOGITS
    个å¤ļ
    0.12
    éĴī
    0.10
     semi
    0.10
    åħļæł¡
    0.09
    uters
    0.09
    è½½
    0.09
    个å¤ļæľĪ
    0.09
    çŁ¥åIJįçļĦ
    0.09
    åħ¬æĬ¥
    0.09
    semi
    0.09
    Activations Density 0.077%

    No Known Activations