© 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. 31276
    Prev
    Next
    INDEX
    Explanations

    Texture, ubiquitous, ical, sla

    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
    믹
    -0.10
    注åħ¥
    -0.09
    èĪŀè¹Ī
    -0.09
    ç¬ij声
    -0.09
     accent
    -0.09
    yat
    -0.08
    åŃĹåı·
    -0.08
    ç¬ijèĦ¸
    -0.08
    Elf
    -0.08
    vent
    -0.08
    POSITIVE LOGITS
    æĿľåħ°
    0.11
    ä¸Ģåı¥è¯Ŀ
    0.10
    è¿ĺåİŁ
    0.10
    éĢ¼è¿ij
    0.10
    gos
    0.09
    åªĴ
    0.09
    ç§ĥ
    0.09
     Licence
    0.09
    éģ¥
    0.09
    metis
    0.09
    Activations Density 0.126%

    No Known Activations