© 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. 5034
    Prev
    Next
    INDEX
    Explanations

    spread and distributed

    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
    çĶĺ
    -0.10
    æıŃ
    -0.09
    andal
    -0.09
    leon
    -0.09
    ungle
    -0.09
    çķĮçļĦ
    -0.08
    éŀł
    -0.08
    èľ·
    -0.08
    åį¡éĢļ
    -0.08
     ÐłÐ¾ÑģÑģий
    -0.08
    POSITIVE LOGITS
    åħ¥åı£
    0.09
    æijĬ
    0.09
    çĿ£
    0.09
    åģļ强
    0.09
    滢
    0.09
    ä¸ī大
    0.09
    ä¸Ģå±Ĥ
    0.08
    peer
    0.08
    è¾ĸåĮº
    0.08
    派人
    0.08
    Activations Density 0.008%

    No Known Activations