© 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. 38839
    Prev
    Next
    INDEX
    Explanations

    signal handling and system service control

    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
     Lub
    -0.10
    å¾Ģ
    -0.10
    é¦Ļèķī
    -0.10
    orgh
    -0.09
     Cooke
    -0.09
    æ¡Ī
    -0.09
    æ¼ķ
    -0.09
    ç¾İè²Į
    -0.09
    çĭŃ
    -0.09
    è·¯èĻİ
    -0.09
    POSITIVE LOGITS
    é¢ijéģĵ
    0.10
    ä¸įæŃ»
    0.08
    èĩªè´Ł
    0.08
    æѤæĸĩ
    0.08
    uli
    0.08
    til
    0.08
    å·¡
    0.08
    è¯Ľ
    0.08
     Indones
    0.08
     Killed
    0.08
    Activations Density 0.260%

    No Known Activations