© 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. 33467
    Prev
    Next
    INDEX
    Explanations

    gan or Gan with suffix

    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
    andre
    -0.10
    æĸŁ
    -0.09
    ensive
    -0.09
    éĤ£æ¬¡
    -0.09
    è·»
    -0.09
    æĻ°
    -0.09
    ize
    -0.08
    NY
    -0.08
    uhn
    -0.08
    FX
    -0.08
    POSITIVE LOGITS
    raig
    0.10
    пп
    0.09
    ãĥIJãĥ¼
    0.09
    ëį°
    0.09
    boom
    0.09
    ilon
    0.09
    /OR
    0.09
    shaw
    0.09
    BODY
    0.08
    ä¿Ŀè¯ģ
    0.08
    Activations Density 0.015%

    No Known Activations