© 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. 18109
    Prev
    Next
    INDEX
    Explanations

    over

    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
    èµ°åĩºåİ»
    -0.09
    cept
    -0.08
    клÑİÑĩениÑı
    -0.08
    born
    -0.08
    æĹłçŁ¥
    -0.08
    级以ä¸Ĭ
    -0.08
    èĢķèĢĺ
    -0.08
    à¹Ĥà¸Ħร
    -0.08
    追赶
    -0.08
     inward
    -0.08
    POSITIVE LOGITS
    éĤ£è¾¹
    0.11
    éļĶå£ģ
    0.10
    çıł
    0.09
    esto
    0.09
    è¶Ĭ好
    0.09
    ãģ¡ãĤĩãģĨãģ©
    0.09
    æ´µ
    0.09
    åIJĮäºĭ
    0.09
    è¿Ļè¾¹
    0.08
    åİ¢
    0.08
    Activations Density 0.011%

    No Known Activations