© 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. 52395
    Prev
    Next
    INDEX
    Explanations

    .gov or .nih

    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
    æĺ¯éĿŀ
    -0.09
    åĮĹç¾İ
    -0.09
     Ltd
    -0.08
     LTD
    -0.08
    交åıĭ
    -0.07
    ä¸Ģæĸ¹
    -0.07
    ç»ķ
    -0.07
    icine
    -0.07
    æľ¬åħ¬åı¸
    -0.07
    뢰
    -0.07
    POSITIVE LOGITS
    åħ¬åĬ¡åijĺ
    0.12
    æĶ¿åºľéĩĩè´Ń
    0.12
    .nih
    0.12
    WASHINGTON
    0.11
    .gov
    0.11
    åĬŀåħ¬åİħ
    0.11
    信访
    0.10
    åī¯å±Ģéķ¿
    0.10
    åĽ½å®¶çº§
    0.10
    å±Ģéķ¿
    0.10
    Activations Density 0.165%

    No Known Activations