© 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. 22702
    Prev
    Next
    INDEX
    Explanations

    in-depth analysis or review

    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
    é¬
    -0.11
    çĦ¶
    -0.09
    ighton
    -0.09
    tered
    -0.09
    ows
    -0.09
    place
    -0.09
    arning
    -0.09
    бо
    -0.09
    rops
    -0.08
     competent
    -0.08
    POSITIVE LOGITS
    elig
    0.10
    eree
    0.09
    åĿŀ
    0.09
    à¹Ģà¸īà¸ŀาะ
    0.09
    æ¯ıä¸Ģ个
    0.08
    rick
    0.08
    å½»åºķ
    0.08
    èĶĵ
    0.08
    马æĭīæĿ¾
    0.08
    erval
    0.08
    Activations Density 0.003%

    No Known Activations