© 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. 56475
    Prev
    Next
    INDEX
    Explanations

    random selection

    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
    esk
    -0.10
    argon
    -0.09
    æĺ¯ä»¥
    -0.09
    æ»ļçIJĥ
    -0.09
    ä¸ĩ象
    -0.09
    stones
    -0.09
    _AMD
    -0.09
    моÑĤ
    -0.09
    å¿ĥéĩĮ
    -0.09
    åĬ²
    -0.08
    POSITIVE LOGITS
    =random
    0.14
     random
    0.13
    /random
    0.13
    æĬ½æŁ¥
    0.12
    éļıæľº
    0.12
    .Random
    0.12
    random
    0.12
    (random
    0.12
     ÑģлÑĥÑĩай
    0.12
    .random
    0.11
    Activations Density 0.097%

    No Known Activations