© 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. 4755
    Prev
    Next
    INDEX
    Explanations

    classification schemes

    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
    çĻ½é¢Ĩ
    -0.10
    æłī
    -0.09
    身边çļĦ
    -0.09
    æĢ»æķ°
    -0.09
    icional
    -0.08
    åįķåįķ
    -0.08
    è¹Ī
    -0.08
     premise
    -0.08
    åı¯ä¿¡
    -0.08
    åĨħåŃĺ
    -0.08
    POSITIVE LOGITS
    å°ĺ
    0.10
    ensch
    0.09
    _hal
    0.09
    emplate
    0.09
     topics
    0.09
    æĴ©
    0.09
    ged
    0.09
    è°ĥæĸĻ
    0.09
    æŀ¶
    0.08
    éĵ¡
    0.08
    Activations Density 0.050%

    No Known Activations