© 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. 4852
    Prev
    Next
    INDEX
    Explanations

    unveiling or debuted

    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
    _UNDEF
    -0.09
    untime
    -0.09
    oner
    -0.08
    หวย
    -0.08
    anker
    -0.08
     clue
    -0.08
    à¸Ľà¸²à¸ģ
    -0.08
    yles
    -0.08
    _pdu
    -0.08
    å¾Īå¿«
    -0.08
    POSITIVE LOGITS
    çłĶ究æĪIJæŀľ
    0.12
    äº®çĽ¸
    0.12
    éķ¿çĽ¸
    0.09
    uster
    0.09
    rst
    0.09
    åºIJ
    0.09
    æĨĭ
    0.09
    ç¬ijèĦ¸
    0.09
    æĪIJæŀľ
    0.09
    å®ıä¼Ł
    0.09
    Activations Density 0.014%

    No Known Activations