© 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. 27274
    Prev
    Next
    INDEX
    Explanations

    countries and military affairs

    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
    .EX
    -0.10
     Scotch
    -0.09
    累积
    -0.09
    åĩĿèģļ
    -0.09
    unan
    -0.08
    æĶ¶æ¬¾
    -0.08
    åĮĻ
    -0.08
    ยà¸ģ
    -0.08
    apes
    -0.08
    _ARG
    -0.08
    POSITIVE LOGITS
    ä¸Ĭåı¸
    0.10
    ä¸Ģæĸ¹
    0.09
    çļ®èĤ¤çĹħ
    0.09
    åIJĮè¡Į
    0.09
    èĢģæĿ¿
    0.08
    æ¯Ķäºļ
    0.08
    ITS
    0.08
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    åľ¨å½ĵåľ°
    0.08
    .descriptor
    0.08
    Activations Density 0.387%

    No Known Activations