© 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. 26549
    Prev
    Next
    INDEX
    Explanations

    image compression jargon

    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
    inker
    -0.10
    åįģä½³
    -0.09
    ouro
    -0.09
     Epstein
    -0.08
     Flip
    -0.08
    åĮ¿åIJį
    -0.08
    .flip
    -0.08
    ãĤ¢ãĥĬ
    -0.08
    太快
    -0.08
    ÑģÑĤÑĭ
    -0.08
    POSITIVE LOGITS
    åİĭ缩
    0.11
    ä¼łçľŁ
    0.10
    è±Ĩ
    0.09
    ÑĥÑħ
    0.09
    æįŁå¤±
    0.09
     reap
    0.08
    ITU
    0.08
    人们对
    0.08
    ision
    0.08
    manship
    0.08
    Activations Density 0.166%

    No Known Activations