© 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. 55671
    Prev
    Next
    INDEX
    Explanations

    part 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
    æŶæĬ¥
    -0.11
    éºŁ
    -0.09
    osity
    -0.09
    éĴī
    -0.09
    /disable
    -0.09
    azi
    -0.09
    ç´¢åıĸ
    -0.09
    inz
    -0.08
    涯
    -0.08
     Fal
    -0.08
    POSITIVE LOGITS
    icular
    0.14
    tern
    0.13
    ners
    0.13
    icipant
    0.13
    icipants
    0.12
    ราà¸Ĭà¸ģาร
    0.11
    isans
    0.10
    icip
    0.10
    TERN
    0.10
    cular
    0.10
    Activations Density 0.095%

    No Known Activations