© 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. 23382
    Prev
    Next
    INDEX
    Explanations

    absorb

    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»ĭ
    -0.10
    vard
    -0.09
    éļ¾
    -0.09
    æī¿è®¤
    -0.09
    èĪ£
    -0.09
    oldt
    -0.09
    éĥĽ
    -0.09
    æ³¼
    -0.08
    ãģŀ
    -0.08
    ipur
    -0.08
    POSITIVE LOGITS
    æ£īèĬ±
    0.14
     cotton
    0.13
    æ£ī
    0.12
     Cotton
    0.10
    ä¸Ģç»ı
    0.10
    çĻ½è¡£
    0.09
    æĿŁ
    0.09
    æĵ¦æĭŃ
    0.09
    è´£ç¼ĸ
    0.09
    纺
    0.09
    Activations Density 0.107%

    No Known Activations