© 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. 49372
    Prev
    Next
    INDEX
    Explanations

    mug or Mugabe

    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
    å¯ĨåĪĩåħ³æ³¨
    -0.09
    itle
    -0.09
    _DECLS
    -0.09
    ibles
    -0.09
    .WinForms
    -0.09
    enne
    -0.08
    uzzi
    -0.08
    enso
    -0.08
     "('
    -0.08
    emand
    -0.08
    POSITIVE LOGITS
    aber
    0.11
    trap
    0.10
    hole
    0.10
     mug
    0.09
     ХоÑĤ
    0.09
    shots
    0.09
    itude
    0.09
    hots
    0.09
    grav
    0.09
    rok
    0.09
    Activations Density 0.004%

    No Known Activations