© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40099
    Prev
    Next
    INDEX
    Explanations

    goodness, insanity, madness, greatness

    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
    ster
    -0.11
    ÑĤан
    -0.10
    å¨ĥ
    -0.09
    樯
    -0.09
    æ±īåŃIJ
    -0.09
    侯
    -0.09
    soever
    -0.09
    åīįæīĢ
    -0.09
     Ø´ÙĬ
    -0.09
    çļĦæĵįä½ľ
    -0.09
    POSITIVE LOGITS
    çĴŀ
    0.09
    ÑģÑĤвеннÑĭй
    0.09
    oso
    0.08
    æĿ²
    0.08
    ingham
    0.08
    ingers
    0.08
    hue
    0.08
    æĬ«
    0.08
    inger
    0.08
    lah
    0.08
    Activations Density 0.005%

    No Known Activations