© 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. 61746
    Prev
    Next
    INDEX
    Explanations

    US states and locations

    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
    efault
    -0.09
    æİĤ
    -0.08
    æĽ´å¿«
    -0.08
    æĢ¨
    -0.08
    çľĭä½ł
    -0.08
    erate
    -0.08
     publications
    -0.07
    fault
    -0.07
    å·«
    -0.07
    .dy
    -0.07
    POSITIVE LOGITS
    迹
    0.12
    éģĹ产
    0.11
    ç±į
    0.10
    çĶŁãģ¾ãĤĮ
    0.09
    侨
    0.09
    家éĩĮ
    0.09
    æĪ·ç±į
    0.09
    ITA
    0.09
    åĽ½åľŁ
    0.09
    æĪ·åı£
    0.09
    Activations Density 0.013%

    No Known Activations