© 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. 32222
    Prev
    Next
    INDEX
    Explanations

    potential followed by a noun

    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
    agt
    -0.10
    èĮĨ
    -0.10
    æľ¬è´¨ä¸Ĭ
    -0.10
    è°ª
    -0.09
    å¾Ģå¾Ģä¼ļ
    -0.09
    (es
    -0.09
    roc
    -0.09
    ication
    -0.09
    èĪĽ
    -0.09
    csr
    -0.08
    POSITIVE LOGITS
    ities
    0.14
    mente
    0.13
    idades
    0.12
    ités
    0.11
    elves
    0.11
    ted
    0.11
    idad
    0.10
    amp
    0.10
    .FR
    0.10
    ìłģìľ¼ë¡ľ
    0.10
    Activations Density 0.021%

    No Known Activations