© 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. 55321
    Prev
    Next
    INDEX
    Explanations

    copyright statements

    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
    å¿ĥæĦı
    -0.11
    æ©Ħæ¦Ħ
    -0.09
    åĥŃ
    -0.09
    夫
    -0.09
    åıĻ
    -0.08
    unk
    -0.08
     ÑĥÑģпеÑĪ
    -0.08
    æĹ¶ä»£ä¸ŃåĽ½
    -0.08
    æĪĺåĽ½
    -0.08
    æĢĿæĥ³æĶ¿æ²»
    -0.08
    POSITIVE LOGITS
    gado
    0.09
    allen
    0.09
    enville
    0.09
    é£ŀè·ĥ
    0.08
    _COLL
    0.08
    raid
    0.08
    render
    0.08
    änn
    0.08
    注æĦıåĪ°
    0.08
    baugh
    0.08
    Activations Density 0.099%

    No Known Activations