© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36292
    Prev
    Next
    INDEX
    Explanations

    names and locations

    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
    以èī²
    -0.10
    åħ·æľīä¸Ģå®ļ
    -0.09
    ertz
    -0.09
    éĢĤå½ĵ
    -0.09
    毫ä¸į
    -0.09
    éĥĥ
    -0.09
    éĹ»åIJį
    -0.09
    é¼ĵ
    -0.09
    èĻĶ
    -0.09
    çºłæŃ£
    -0.09
    POSITIVE LOGITS
    sons
    0.10
    çļĦæĪIJ绩
    0.09
     dik
    0.08
    è¿Ľä¸ĢæŃ¥
    0.08
    seed
    0.08
    .getItems
    0.08
     Decre
    0.08
    ä¸įå°½
    0.08
    preh
    0.08
    ipop
    0.08
    Activations Density 0.138%

    No Known Activations