© 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. 55724
    Prev
    Next
    INDEX
    Explanations

    official policy, not involved

    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
    uchi
    -0.09
    ngth
    -0.08
     discretion
    -0.08
    åŀ£
    -0.08
    ай
    -0.08
    cratch
    -0.08
    åħį责声æĺİ
    -0.08
    è¯ļå®ŀ
    -0.08
    borg
    -0.08
    é£İåħī
    -0.08
    POSITIVE LOGITS
    å¸Ī
    0.09
    æĿ¯
    0.09
    åħµ
    0.09
    çĥĽ
    0.09
    èĤ±
    0.09
    姿
    0.09
    åĭĴ
    0.09
    èĵij
    0.09
    ä¾Ŀæ³ķ追究
    0.09
    çłĸ
    0.09
    Activations Density 0.012%

    No Known Activations