© 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. 56258
    Prev
    Next
    INDEX
    Explanations

    copyright or license

    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
    åģļèµ·
    -0.08
    åľ¨å½ĵåľ°
    -0.08
    åĽ½åĬ¡
    -0.08
    éģĩéļ¾
    -0.08
    æ´¼
    -0.07
    åĿĩ
    -0.07
    åµĺ
    -0.07
     unarmed
    -0.07
    è¾°
    -0.07
    å¹´åĨħ
    -0.07
    POSITIVE LOGITS
    sWith
    0.10
     COPYRIGHT
    0.10
    usercontent
    0.09
    PropertyParams
    0.09
    SupportedContent
    0.09
    èĩªçĦ¶æĺ¯
    0.09
     Jew
    0.09
    ë¡ł
    0.09
    éĤ³
    0.09
     ÑģкаÑĩ
    0.09
    Activations Density 0.570%

    No Known Activations