© 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. 48811
    Prev
    Next
    INDEX
    Explanations

    span, spanning, or related measurements

    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
    wards
    -0.10
    ãĤ«ãĥª
    -0.10
    ä¸įçĦ¶
    -0.09
    ç½²
    -0.08
    ãĤį
    -0.08
     McGu
    -0.08
     siden
    -0.08
    svp
    -0.08
    uze
    -0.08
    aurant
    -0.08
    POSITIVE LOGITS
    ned
    0.18
    nable
    0.17
    ning
    0.14
    iards
    0.13
     Ñģобой
    0.11
    aroo
    0.11
    xiety
    0.10
    erville
    0.10
    è´
    0.10
    TURE
    0.10
    Activations Density 0.026%

    No Known Activations