© 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. 49778
    Prev
    Next
    INDEX
    Explanations

    Personally I

    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
    .apple
    -0.08
    è¾ľè´Ł
    -0.08
    åıł
    -0.08
     issuing
    -0.08
    ä¸Ī
    -0.08
    å¦ĤæѤ
    -0.08
    æ¯ķç«Ł
    -0.08
    heap
    -0.07
     discord
    -0.07
    éĿ©
    -0.07
    POSITIVE LOGITS
     пока
    0.10
    æĪijä¸į
    0.10
    楼ä¸Ĭ
    0.09
    æĪij个人
    0.09
    æĤłæĤł
    0.09
    ately
    0.09
    ("'"
    0.09
    .setInput
    0.09
    ively
    0.09
    对äºİæĪij们
    0.09
    Activations Density 0.010%

    No Known Activations