© 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. 31988
    Prev
    Next
    INDEX
    Explanations

    blues music song

    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
     Malone
    -0.11
    _GRE
    -0.10
    ầy
    -0.09
    æĬĬèĩªå·±çļĦ
    -0.09
    æķıéĶIJ
    -0.09
    _NM
    -0.09
    沫
    -0.09
    åĭ¢
    -0.09
    _COMBO
    -0.09
    è¯Ľ
    -0.09
    POSITIVE LOGITS
    FORMAT
    0.08
    å½ĵåľº
    0.08
    rozen
    0.08
    uster
    0.08
    /layouts
    0.08
     FORMAT
    0.08
    jang
    0.08
    åİĨ
    0.08
    *
    0.08
    寡
    0.08
    Activations Density 0.096%

    No Known Activations