© 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. 32199
    Prev
    Next
    INDEX
    Explanations

    members and associates

    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
    çIJĨ论ä¸Ĭ
    -0.09
    åįłåľ°éĿ¢ç§¯
    -0.09
     theor
    -0.09
    è¿ŀè½½
    -0.09
    夺å¾Ĺ
    -0.08
    çĦ¦
    -0.08
    客è¿IJ
    -0.08
    rud
    -0.08
    æĭ¯
    -0.08
    人身
    -0.08
    POSITIVE LOGITS
    ä¹Łå¾Ī
    0.11
    ä¸ij
    0.11
    æijĩ
    0.10
    ç¹ģèį£
    0.10
    çĶ·æĸ¹
    0.09
    ifter
    0.09
    ä¸į对
    0.09
    è¯Ħä»·
    0.09
    ç§ijåѦéĻ¢
    0.09
    èµĦåĬ©
    0.09
    Activations Density 0.080%

    No Known Activations