© 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. 36494
    Prev
    Next
    INDEX
    Explanations

    height properties

    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
    æĢ§å¼º
    -0.10
    owell
    -0.09
    hip
    -0.09
     hô
    -0.09
    妪
    -0.09
    ä¸ľæµ·
    -0.08
    irth
    -0.08
    rit
    -0.08
    ritte
    -0.08
    strate
    -0.08
    POSITIVE LOGITS
    ened
    0.18
    ening
    0.15
    inous
    0.11
    OfFile
    0.10
    MeasureSpec
    0.10
    åIJĪãģĦ
    0.10
    лÑİб
    0.09
    t
    0.09
    ens
    0.09
    /power
    0.09
    Activations Density 0.096%

    No Known Activations