© 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. 48492
    Prev
    Next
    INDEX
    Explanations

    list items separated by commas

    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
    å¾Ĺ天
    -0.10
    å§Ŀ
    -0.10
    /kubernetes
    -0.09
    ç®Ģ称
    -0.09
    æ¾Ħæ¸ħ
    -0.09
    客æ°Ķ
    -0.09
    æį¢åı¥è¯Ŀ
    -0.09
    硼
    -0.09
    çļĦ年轻人
    -0.09
    tsky
    -0.09
    POSITIVE LOGITS
    åĩºåħ¥
    0.09
    èİ«è¿ĩäºİ
    0.09
    ote
    0.08
    OTE
    0.08
    “
    0.08
    éĺħ
    0.08
     Gent
    0.08
     Sent
    0.07
    sent
    0.07
    Aware
    0.07
    Activations Density 0.072%

    No Known Activations