© 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. 6634
    Prev
    Next
    INDEX
    Explanations

    in the preceding tokens

    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
    éĢIJå¹´
    -0.10
    æĶ¯
    -0.09
    _Parms
    -0.09
    å°¼æĸ¯
    -0.09
    éű
    -0.09
    обÑĢа
    -0.09
    æĥĽ
    -0.09
    -Feb
    -0.08
    Anywhere
    -0.08
    奸
    -0.08
    POSITIVE LOGITS
    agic
    0.09
    ç±³é¥Ń
    0.08
    .TryParse
    0.08
    èĥŃ
    0.08
    è¶Ĭ
    0.08
    鼶è·Ŀ离
    0.08
    ç»ĻäºĨ
    0.08
    Ø®ÙĦ
    0.08
    èĩ´åĬĽ
    0.08
    ansi
    0.08
    Activations Density 0.017%

    No Known Activations