© 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. 34469
    Prev
    Next
    INDEX
    Explanations

    not play or not advance

    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
    yne
    -0.09
    æŃª
    -0.09
    ateg
    -0.09
    ä¼Ļ
    -0.09
    æĶ¾è¿ĩ
    -0.09
     Speedway
    -0.09
    ucas
    -0.09
    yers
    -0.08
    _ASCII
    -0.08
    èµ·çłģ
    -0.08
    POSITIVE LOGITS
    åıij声
    0.09
    è¾ľè´Ł
    0.09
    è´µ
    0.09
    èĶ»
    0.09
     KE
    0.08
    ä¸į容
    0.08
    éķ¬
    0.08
    бол
    0.08
    åıĹéĻIJ
    0.08
    çIJ¢
    0.08
    Activations Density 0.025%

    No Known Activations