© 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. 22799
    Prev
    Next
    INDEX
    Explanations

    burden or load

    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
    éĽĨæĪIJ
    -0.10
    ä¸įéĶĻ
    -0.09
    åĿĹ
    -0.09
    scribers
    -0.09
    uo
    -0.09
    اج
    -0.09
    ARN
    -0.09
    éĻIJåĪ¶
    -0.08
    åįı
    -0.08
    éĵº
    -0.08
    POSITIVE LOGITS
    ä¸įåłª
    0.10
    èĤ©è´Ł
    0.10
    èĤ´
    0.10
     strained
    0.10
    çĸ²
    0.09
    礼è²Į
    0.09
    _APPS
    0.09
     strain
    0.08
    oun
    0.08
    ä¸įè´Ł
    0.08
    Activations Density 0.083%

    No Known Activations