© 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. 1325
    Prev
    Next
    INDEX
    Explanations

    ritus. sacrum. encyclopaedias

    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
     tar
    -0.09
    çľŁç©º
    -0.09
    tics
    -0.09
    lyph
    -0.09
    .tar
    -0.09
    éĹ´çļĦ
    -0.08
    ISON
    -0.08
    çķĪ
    -0.08
    icot
    -0.08
    åĭ¾
    -0.08
    POSITIVE LOGITS
    èĢĮæĿ¥
    0.10
    为åĩĨ
    0.09
    æľīåĬ©
    0.09
    amus
    0.09
    åįĬ个
    0.09
    æĭ©
    0.09
    ssel
    0.09
    ç½ijå°ıç¼ĸ
    0.08
    (success
    0.08
    ç¥ŀå·ŀ
    0.08
    Activations Density 0.123%

    No Known Activations