© 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. 35080
    Prev
    Next
    INDEX
    Explanations

    using up or exhausting resources

    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
    ANTE
    -0.10
    gio
    -0.10
    afia
    -0.09
    ibold
    -0.09
    ä¸ĵä¸ļåĮĸ
    -0.09
    NotSupportedException
    -0.09
    ìĥ¤
    -0.09
    otor
    -0.09
    áb
    -0.09
    çĢijå¸ĥ
    -0.09
    POSITIVE LOGITS
    lo
    0.09
    ç¨Ĺ
    0.08
    (...)
    0.08
     ons
    0.08
    ery
    0.08
    èĭį
    0.08
    loit
    0.07
    çĸĹç¨ĭ
    0.07
    æ³®
    0.07
    éĻ
    0.07
    Activations Density 0.005%

    No Known Activations