© 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. 3926
    Prev
    Next
    INDEX
    Explanations

    pl., INT., .Pr, associated

    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
     Horton
    -0.08
    _tE
    -0.08
    éŃĶæľ¯
    -0.08
    ç®į
    -0.08
     nuru
    -0.08
    -END
    -0.08
    çĢij
    -0.08
    _buffers
    -0.08
    orce
    -0.08
    idend
    -0.08
    POSITIVE LOGITS
    ฯ
    0.12
     Univ
    0.10
    .,
    0.09
    çĦ¶æĺ¯
    0.09
    å§Ķ
    0.09
    å°±å¾Ĺ
    0.09
    ä¹ł
    0.08
    人社å±Ģ
    0.08
    åĥ»
    0.08
    åIJĦå¼Ĥ
    0.08
    Activations Density 0.389%

    No Known Activations