© 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. 4877
    Prev
    Next
    INDEX
    Explanations

    seeing more

    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
    ä¸ĩ家
    -0.11
    ewidth
    -0.11
    æĬ¥ç¤¾
    -0.09
    elor
    -0.09
    è°ģèĥ½
    -0.09
    oola
    -0.09
    éĨ
    -0.09
     ìĸ¸
    -0.09
    çļĦçģµéŃĤ
    -0.09
    ä½łèĥ½
    -0.09
    POSITIVE LOGITS
    åīįæĿ¥
    0.10
    客æĪ·éľĢæ±Ĥ
    0.10
    æĬĦ
    0.09
    èĬĤ
    0.09
     Requests
    0.09
    éĹ®è¯¢
    0.09
    æİ¥åĪ°
    0.09
    çĸ²
    0.08
     gag
    0.08
    客æĪ·
    0.08
    Activations Density 0.045%

    No Known Activations