© 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. 55755
    Prev
    Next
    INDEX
    Explanations

    bank sheets Bus .net Bible Wizard Forest plug

    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
    -0.08
    %C
    -0.08
    uja
    -0.08
     octave
    -0.08
    ola
    -0.07
    á»ħn
    -0.07
    hra
    -0.07
    drawing
    -0.07
    en
    -0.07
     the
    -0.07
    POSITIVE LOGITS
    ä¹ĭ家
    0.13
    æľ¬èº«çļĦ
    0.11
    ฯ
    0.11
    管çIJĨåĴĮ
    0.11
    ä¹ĭæĺŁ
    0.11
    æľ¬èº«
    0.10
    ä¹ĭåĪĿ
    0.10
    礼çī©
    0.09
    æĹ¥æĬ¥ç¤¾
    0.09
    è¿Ļä¹Īä¹ħ
    0.09
    Activations Density 1.490%

    No Known Activations