© 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. 63197
    Prev
    Next
    INDEX
    Explanations

    filled thermometer, bubble towards, sensitive movable

    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
    utm
    -0.09
    çĶµçº¿
    -0.09
    argo
    -0.08
     Legion
    -0.08
    unication
    -0.08
    ibbon
    -0.08
    addon
    -0.08
    ILINE
    -0.08
    ordinates
    -0.08
    iba
    -0.08
    POSITIVE LOGITS
    é¢ľ
    0.10
    æ°Ľ
    0.10
    å¼Ģåĩº
    0.10
    æĭ³
    0.09
    饥
    0.09
     coward
    0.09
    æ¼ķ
    0.09
    é£ĺ
    0.09
    åĽŃ
    0.09
    åĿĹ
    0.08
    Activations Density 0.089%

    No Known Activations