© 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. 38791
    Prev
    Next
    INDEX
    Explanations

    your browser

    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
    åIJİæĤĶ
    -0.10
    еÑĢÑĭ
    -0.10
     lem
    -0.09
     ere
    -0.09
    åĶ
    -0.08
    ire
    -0.08
    æ¸ļ
    -0.08
     enh
    -0.08
    åıijæĮ¥ä½ľçĶ¨
    -0.08
     dt
    -0.08
    POSITIVE LOGITS
    åħ½
    0.09
    _space
    0.09
    棻
    0.09
    ä½İè°ĥ
    0.08
    认为
    0.08
    ä¸įä½³
    0.08
    oggler
    0.08
     Büyük
    0.08
    Æ¡
    0.08
    ocard
    0.08
    Activations Density 0.045%

    No Known Activations