© 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. 17364
    Prev
    Next
    INDEX
    Explanations

    suspension

    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
    umen
    -0.10
    bserv
    -0.10
    lesia
    -0.09
    æ»ļæ»ļ
    -0.09
     Aurora
    -0.08
    ops
    -0.08
    微微
    -0.08
    ä¸ĢæŃ¥æŃ¥
    -0.08
    ãĥĥãĤ·
    -0.08
    damn
    -0.08
    POSITIVE LOGITS
    ently
    0.11
    ively
    0.11
    ably
    0.10
    ãģĴ
    0.09
    ary
    0.09
    mounted
    0.09
    writers
    0.09
    ned
    0.09
    ency
    0.09
    ry
    0.08
    Activations Density 0.034%

    No Known Activations