© 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. 39019
    Prev
    Next
    INDEX
    Explanations

    years ago, years of

    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
    anon
    -0.09
    ç©´
    -0.09
    portal
    -0.09
    unar
    -0.09
    å®īå±ħ
    -0.09
    è¯ķçĤ¹
    -0.09
    åįĬå¹´
    -0.08
    ç©°
    -0.08
    ización
    -0.08
    天ä¸ĭ
    -0.08
    POSITIVE LOGITS
    çłº
    0.11
    èĮĦ
    0.10
    æľ¬ç«Ļ
    0.09
    ustr
    0.09
    ãĢħ
    0.09
    æĬī
    0.09
    温馨æıIJ示
    0.09
    -old
    0.08
    å¤ļå¹´
    0.08
    Lens
    0.08
    Activations Density 0.027%

    No Known Activations