© 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. 55462
    Prev
    Next
    INDEX
    Explanations

    metric tons, tonnes, tons

    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
    olson
    -0.10
     vir
    -0.09
    agal
    -0.09
    çĭ©
    -0.09
    Leap
    -0.09
    æĶĺ
    -0.08
    /pm
    -0.08
    rea
    -0.08
    (IC
    -0.08
     seam
    -0.08
    POSITIVE LOGITS
    é©´
    0.13
    tractor
    0.10
    å¨ī
    0.10
    西äºļ
    0.10
    驼
    0.10
    çŃIJ
    0.10
    骡
    0.09
    tract
    0.09
    è¾İ
    0.09
     живоÑĤ
    0.09
    Activations Density 0.057%

    No Known Activations