© 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. 1926
    Prev
    Next
    INDEX
    Explanations

    license terms for use

    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
    -os
    -0.09
     tap
    -0.09
    agens
    -0.09
    俾
    -0.08
    ä¸į满æĦı
    -0.08
    asc
    -0.08
    åį¡
    -0.08
    åĿį
    -0.08
    å®īæ£Ģ
    -0.08
    æĤ¬
    -0.08
    POSITIVE LOGITS
     Trot
    0.10
     reproduce
    0.10
    RIES
    0.10
    ERY
    0.10
    .updateDynamic
    0.10
    owy
    0.09
    èĦī
    0.09
    Lng
    0.09
    _PHP
    0.09
    BindingUtil
    0.09
    Activations Density 0.008%

    No Known Activations