© 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. 26093
    Prev
    Next
    INDEX
    Explanations

    fund-amental / fundraising

    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
    ãĥ³ãĤ°
    -0.10
    ened
    -0.10
    ity
    -0.10
    ../../../
    -0.10
    hood
    -0.10
    ../../
    -0.09
    cott
    -0.09
    plier
    -0.09
    è¿ĩçļĦ
    -0.09
    ä¸ĵ项æĸĹäºī
    -0.08
    POSITIVE LOGITS
    amentals
    0.18
    amental
    0.16
    raise
    0.13
    raising
    0.12
    ings
    0.12
    usc
    0.11
    ament
    0.11
    aments
    0.10
    ishing
    0.10
    stead
    0.10
    Activations Density 0.023%

    No Known Activations