© 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. 33819
    Prev
    Next
    INDEX
    Explanations

    made in

    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
    åijĺ
    -0.10
    aire
    -0.09
    dre
    -0.09
    пÑĢавлÑı
    -0.08
    icide
    -0.08
    plusplus
    -0.08
     Marble
    -0.08
    æĬĬæĮģ
    -0.08
    leton
    -0.08
    cry
    -0.08
    POSITIVE LOGITS
    ckt
    0.10
    çĶľç¾İ
    0.09
    éģı
    0.09
    ä¸įå°ıçļĦ
    0.08
    orra
    0.08
    coli
    0.08
     ÑĥвелиÑĩи
    0.08
     ÑĢож
    0.08
    uled
    0.08
    ymb
    0.08
    Activations Density 0.026%

    No Known Activations