© 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. 34482
    Prev
    Next
    INDEX
    Explanations

    dear friend, reader, sir, lord

    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
    涯
    -0.11
    azzi
    -0.09
    ally
    -0.09
    èĪĴå¿ĥ
    -0.09
    kre
    -0.09
    ÑĢеÑĪ
    -0.09
    æµģæĺŁ
    -0.09
    aze
    -0.09
    çīĴ
    -0.09
    é£İæĥħ
    -0.08
    POSITIVE LOGITS
     dÃłng
    0.11
    liest
    0.11
    ODB
    0.09
    chant
    0.09
    WARE
    0.09
    زÙĨ
    0.09
    ä¸įçĦ¶
    0.09
    ement
    0.09
    åģļå®Į
    0.09
    ITY
    0.09
    Activations Density 0.002%

    No Known Activations