© 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. 62047
    Prev
    Next
    INDEX
    Explanations

    at least, though

    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
    åıĮè¾¹
    -0.10
    oho
    -0.10
    äºĮ线
    -0.09
    eral
    -0.09
    åįĥéĩĮ
    -0.09
     Ñģебе
    -0.09
    åıįæŃ£
    -0.09
    essional
    -0.09
    åĢį
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
    POSITIVE LOGITS
    éĹ´æİ¥
    0.09
    hem
    0.08
    _way
    0.08
    åĩĨ
    0.08
    æĮ¯åħ´
    0.08
     tram
    0.07
    æ³ķåĪ¶
    0.07
     Way
    0.07
    put
    0.07
    wine
    0.07
    Activations Density 0.015%

    No Known Activations