© 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. 11761
    Prev
    Next
    INDEX
    Explanations

    sailing, boats, sailor

    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
    æ¦Ľ
    -0.09
    è´´å¿ĥ
    -0.09
    çĶ©
    -0.09
    íĿ¥
    -0.08
    jem
    -0.08
    å¹¼ç¨ļ
    -0.08
    algo
    -0.08
    å®ĺ
    -0.08
    gene
    -0.08
    .Default
    -0.08
    POSITIVE LOGITS
    ä»İå°ı
    0.09
    æıŃ
    0.09
    _POLL
    0.09
    è³½
    0.09
    èµĽ
    0.09
     trúc
    0.09
     Grat
    0.09
    Ñĥл
    0.09
    Race
    0.09
    ç«ŀäºī
    0.08
    Activations Density 0.064%

    No Known Activations