© 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. 62857
    Prev
    Next
    INDEX
    Explanations

    in the lives or minds of

    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
    åı²
    -0.09
    ç»ıèIJ¥èĮĥåĽ´
    -0.08
    enis
    -0.08
    iss
    -0.08
     suffered
    -0.08
    åīįæĻ¯
    -0.07
    аÑĢÑĮ
    -0.07
    åı¯æĥľ
    -0.07
    ExecutionContext
    -0.07
    iba
    -0.07
    POSITIVE LOGITS
    çݩ家æĿ¥è¯´
    0.10
    è¶Ĭæĺ¯
    0.10
    ntax
    0.09
    çªģåĩ»
    0.09
    OND
    0.09
    们
    0.09
    款
    0.09
    ond
    0.09
    ertain
    0.09
    æİ¥åĪ°
    0.09
    Activations Density 0.180%

    No Known Activations