© 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. 38816
    Prev
    Next
    INDEX
    Explanations

    timestamps with colons

    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
    æį§
    -0.09
    äge
    -0.09
    åįľ
    -0.08
     Municip
    -0.08
    æĿ¥è¿ĻéĩĮ
    -0.08
    .seed
    -0.08
    å¸Ĥæ°ij
    -0.07
    ä»ŀ
    -0.07
    ä¸ĭ乡
    -0.07
    лÑıÑĢ
    -0.07
    POSITIVE LOGITS
    ä¹ĭå¤ľ
    0.11
    æīĢèĥ½
    0.10
    妫
    0.09
    éĩİçĶŁ
    0.09
    åĿŀ
    0.09
    åIJŀ
    0.09
    erland
    0.09
    她说
    0.09
    avi
    0.09
    ä»ħ代表
    0.09
    Activations Density 0.072%

    No Known Activations