© 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. 53902
    Prev
    Next
    INDEX
    Explanations

    months and numbers

    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
    åĩºèº«
    -0.09
    年以æĿ¥
    -0.09
    å°¤åħ¶
    -0.09
    æĸIJ
    -0.09
    åĩºåĽ½
    -0.09
     Aad
    -0.08
    æĬ¢åħĪ
    -0.08
    ä¹ĭåĪĿ
    -0.08
    åħĪåīį
    -0.08
    ä¸įæĩĤ
    -0.08
    POSITIVE LOGITS
    为æŃ¢
    0.16
    ç»ĵæĿŁ
    0.10
    æŃ¢
    0.09
    éĶ¯
    0.09
    _STOP
    0.09
    ç»ĪæŃ¢
    0.08
    atel
    0.08
    nard
    0.08
    /nav
    0.08
    趣
    0.08
    Activations Density 0.192%

    No Known Activations