© 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. 62129
    Prev
    Next
    INDEX
    Explanations

    cases reported, diagnosed, or occurring

    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
    ORN
    -0.11
    çļĦæŶéĹ´éĩĮ
    -0.10
    æīĵèµ¢
    -0.09
    гÑĢÑĥз
    -0.09
    ypo
    -0.09
    ITO
    -0.09
    ä¸Ģä¸ĸ
    -0.09
    ÙĬÙĪÙĨ
    -0.09
    å®ĥ们
    -0.09
    èĤ¸
    -0.08
    POSITIVE LOGITS
    erge
    0.09
    idd
    0.09
    hc
    0.08
    èĻ¹æ¡¥
    0.08
    .le
    0.08
    åįĹå±±
    0.08
    hev
    0.08
     Wel
    0.08
    idis
    0.08
    xico
    0.08
    Activations Density 0.099%

    No Known Activations