© 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. 57688
    Prev
    Next
    INDEX
    Explanations

    United States government or courts

    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
    تÙĩ
    -0.09
     Heb
    -0.09
    åŃIJéĩĮ
    -0.09
    çıŃåŃIJ
    -0.09
    èĢģ人家
    -0.09
    éĥ¨éĺŁ
    -0.08
    å¹´æĿ¥
    -0.08
    erm
    -0.08
    çĶ¬
    -0.08
    è£Ķ
    -0.08
    POSITIVE LOGITS
    boro
    0.11
     اÙĦØ£ÙħرÙĬÙĥÙĬØ©
    0.09
    pig
    0.08
    éļĽ
    0.08
    è¿ĽæŃ¥
    0.08
    cko
    0.08
     slightest
    0.08
    åĬŀäºĭå¤Ħ
    0.08
    ¿
    0.08
    elect
    0.08
    Activations Density 0.046%

    No Known Activations