© 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. 32196
    Prev
    Next
    INDEX
    Explanations

    guests registered

    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
    积水
    -0.12
    éĽĦåİļ
    -0.10
    çī§åľº
    -0.09
    åī¯å±Ģéķ¿
    -0.09
    å°±è¶Ĭ
    -0.09
    oke
    -0.09
    å¸ĤåĮº
    -0.08
    åĨł
    -0.08
    ÑıÑģÑĮ
    -0.08
    夫
    -0.08
    POSITIVE LOGITS
     sạn
    0.09
    满æĦı度
    0.08
    -feature
    0.08
    лив
    0.08
    è¿ĺåı¯
    0.08
    ria
    0.08
    亲人
    0.08
    å®īåħ¨æĦŁ
    0.08
     utter
    0.08
    å¾Ĺèµ·
    0.08
    Activations Density 0.148%

    No Known Activations