© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10017
    Prev
    Next
    INDEX
    Explanations

    not followed by a verb

    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
    ç¥Ŀç¦ı
    -0.09
    åı¯è§ģ
    -0.09
    åĤ¬
    -0.09
    管å§Ķä¼ļ
    -0.09
    jit
    -0.09
    åºıå¹ķ
    -0.08
    utoff
    -0.08
    èļĵ
    -0.08
    ATUS
    -0.08
    amble
    -0.08
    POSITIVE LOGITS
    ä¼ģä¸ļæıIJä¾Ľ
    0.14
     be
    0.11
    lor
    0.10
    ìį¨
    0.10
    ãģĹãģ¾ãģĨ
    0.10
    æıIJä¾ĽæĽ´å¤ļ
    0.09
    è½»æĺĵ
    0.09
    ically
    0.09
    eness
    0.09
    iable
    0.08
    Activations Density 0.010%

    No Known Activations