© 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. 61334
    Prev
    Next
    INDEX
    Explanations

    necrosis or NEC Corporation

    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
    ably
    -0.09
    _AMD
    -0.08
    ernen
    -0.08
    ãģĹãģĭ
    -0.08
     tù
    -0.08
    ÙĬا
    -0.08
     вообÑīе
    -0.08
    تج
    -0.08
    Multiplicity
    -0.07
     grandson
    -0.07
    POSITIVE LOGITS
    aurant
    0.10
    èĩªè´Ł
    0.10
    oad
    0.09
    æ¯ıä¸Ģä½į
    0.09
    çļĦçľ¼åħī
    0.09
    æĤĮ
    0.09
    ä¸į妨
    0.09
     поб
    0.09
    atform
    0.09
    plib
    0.09
    Activations Density 0.012%

    No Known Activations