© 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. 32920
    Prev
    Next
    INDEX
    Explanations

    hold / holding

    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
    aos
    -0.09
     вÑĭполнен
    -0.09
    -photo
    -0.09
    andes
    -0.09
    uncated
    -0.09
    owing
    -0.08
    åĪĨå·¥
    -0.08
    otic
    -0.08
    hood
    -0.08
    èµĸ以
    -0.08
    POSITIVE LOGITS
     onto
    0.10
    æĮģ
    0.10
     MISSING
    0.09
    æ²Ł
    0.09
     mus
    0.08
    æĶ¾ä¸ĭ
    0.08
     swept
    0.08
    iero
    0.08
    cy
    0.08
    fm
    0.08
    Activations Density 0.015%

    No Known Activations