© 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. 1964
    Prev
    Next
    INDEX
    Explanations

    license and copyright terms

    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
     AUTHORS
    -0.10
    çĦī
    -0.09
    raction
    -0.09
    _dot
    -0.09
    _hits
    -0.08
    æĴ¥
    -0.08
    ãģĵãģĨ
    -0.08
    çļĤ
    -0.08
    yr
    -0.08
    ExceptionHandler
    -0.08
    POSITIVE LOGITS
    æĶ¾è¿Ľ
    0.11
    åĩ¹
    0.10
    让å®ĥ
    0.09
    èĬ±å¼Ģ
    0.09
    åģļå®Į
    0.09
    çĶ·åŃ©
    0.09
    åĽłä¸ºå®ĥ
    0.09
    OSC
    0.08
    han
    0.08
    离
    0.08
    Activations Density 0.300%

    No Known Activations