© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40202
    Prev
    Next
    INDEX
    Explanations

    power dissipation and consumption

    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
    Negative Logits
    erate
    -0.11
    年产
    -0.09
    æķ°æį®ä¸Ńå¿ĥ
    -0.09
    è¡Ķ
    -0.09
    æĺİç¡®
    -0.09
    建档
    -0.08
    aming
    -0.08
    çĥĿ
    -0.08
    ipient
    -0.08
    ÙħÙħ
    -0.08
    POSITIVE LOGITS
    룸
    0.08
     Nagar
    0.08
    habi
    0.08
    kö
    0.08
    _rng
    0.08
    åIJĿ
    0.08
    ноÑģÑĤ
    0.08
     usual
    0.08
    æĥľ
    0.08
    über
    0.07
    Activations Density 0.051%

    No Known Activations