© 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. 18345
    Prev
    Next
    INDEX
    Explanations

    stores selling specific items

    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
    éĻIJéĩı
    -0.10
    åľ¨æ¸¸æĪıä¸Ń
    -0.10
    对ä¼ģä¸ļ
    -0.10
    oldt
    -0.09
    æī¶
    -0.09
     Deposit
    -0.09
    åħĥå®Ŀ
    -0.09
    沤
    -0.09
    æľīä¸Ģå®ļçļĦ
    -0.09
    esty
    -0.08
    POSITIVE LOGITS
    ä¸ļ
    0.12
    åİĤ
    0.11
    åĬłå·¥åİĤ
    0.11
    ä¹ĭ家
    0.09
     company
    0.09
    è¡Įä¸ļåıijå±ķ
    0.09
    åŁ¹è®ŃæľºæŀĦ
    0.09
    è¡Įä¸ļçļĦ
    0.09
    æľįåĬ¡ä¸ļ
    0.09
    éļľ
    0.09
    Activations Density 0.233%

    No Known Activations