© 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. 39055
    Prev
    Next
    INDEX
    Explanations

    making for enough

    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
    æĦıå¤ĸ
    -0.09
    åı¨
    -0.09
    亲çĪ±
    -0.09
    uda
    -0.09
    äºĴåĬ©
    -0.09
    ele
    -0.09
    袱
    -0.09
     moto
    -0.08
    é»ij马
    -0.08
    qry
    -0.08
    POSITIVE LOGITS
    ä»ħä»ħ
    0.13
    ä»ħä»ħæĺ¯
    0.11
     mere
    0.11
    åįķåįķ
    0.10
    åİŁæľīçļĦ
    0.10
    çİ°æľīçļĦ
    0.10
    è¿ĺä¸įå¤Ł
    0.10
    寻常
    0.10
    好åĿı
    0.09
    mere
    0.09
    Activations Density 0.019%

    No Known Activations