© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7520
    Prev
    Next
    INDEX
    Explanations

    what's to like

    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
     ÑģÑĤо
    -0.09
    èµ·æĿ¥äºĨ
    -0.09
    CHIP
    -0.08
    å¾ħéģĩ
    -0.08
    nia
    -0.08
     assignable
    -0.08
     Drops
    -0.08
    tri
    -0.08
    azon
    -0.08
    åŃĺåľ¨çļĦ
    -0.07
    POSITIVE LOGITS
    çĽĨ
    0.09
    æŃ»åIJİ
    0.09
    è´»
    0.08
     nấu
    0.08
    obic
    0.08
    çľ©
    0.08
    诱æĥij
    0.08
    igue
    0.08
    纶
    0.08
    åĪļ好
    0.08
    Activations Density 0.004%

    No Known Activations