© 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. 23348
    Prev
    Next
    INDEX
    Explanations

    permission to use or block

    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
    åŁºæľ¬ä¸Ĭéĥ½
    -0.09
    循
    -0.09
    fection
    -0.08
    缨
    -0.08
    çŃ¾
    -0.08
    ä¸ĢèĪ¬
    -0.08
    EMPL
    -0.08
     Giáo
    -0.08
    fections
    -0.08
    throp
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ
    0.13
    ä»»ä½ķ人
    0.13
    ä»»ä½ķä¸Ģ个
    0.13
    ANY
    0.11
    ä»»ä½ķå½¢å¼ı
    0.10
     лÑİбой
    0.10
    æĿİåħĪçĶŁ
    0.10
    any
    0.10
    è¿Ļ对
    0.10
    -any
    0.09
    Activations Density 0.015%

    No Known Activations