© 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. 38876
    Prev
    Next
    INDEX
    Explanations

    pr + ism / imer / act

    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
    åĴª
    -0.10
    绣
    -0.08
    richt
    -0.08
    å¾Ģä¸Ĭ
    -0.08
    akk
    -0.08
    iku
    -0.08
    efa
    -0.08
    æĿĥ
    -0.08
    .levels
    -0.08
    elson
    -0.08
    POSITIVE LOGITS
    inciple
    0.11
    (pr
    0.10
    (PR
    0.10
    iple
    0.10
    incip
    0.10
    /pr
    0.10
    .PR
    0.09
    inceton
    0.09
    -pr
    0.09
    åĩłä¸ªäºº
    0.09
    Activations Density 0.039%

    No Known Activations