© 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. 2956
    Prev
    Next
    INDEX
    Explanations

    not / no

    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
    ä¸įæŃ¢
    -0.10
    ä¸įä»ħä»ħæĺ¯
    -0.10
    ä¸įå¤Ł
    -0.09
    æŁı
    -0.09
    åħ¬æŃ£
    -0.09
    ä¸įä»ħæĺ¯
    -0.09
    没æ³ķ
    -0.09
    çĶŁåŃĺ
    -0.09
    ä¸įèĤ¯
    -0.09
    ä¸įåģľçļĦ
    -0.09
    POSITIVE LOGITS
     worry
    0.12
     worrying
    0.11
    abei
    0.11
    /lists
    0.10
    å½±åĵį
    0.10
    æĭħå¿ĥ
    0.10
    æ°Ĺãģ«ãģªãĤĭ
    0.10
    åľ¨æĦı
    0.10
    æįŁå®³
    0.10
     worries
    0.09
    Activations Density 0.201%

    No Known Activations