© 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. 63796
    Prev
    Next
    INDEX
    Explanations

    seeds and planting

    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
    åĻ¤
    -0.09
    _ALLOC
    -0.09
    onom
    -0.09
    åķĨåĬ¡
    -0.09
    sted
    -0.09
    å®ļä½į
    -0.08
    blas
    -0.08
    wr
    -0.08
     pub
    -0.08
    arness
    -0.08
    POSITIVE LOGITS
    ç§įåŃIJ
    0.26
     seeds
    0.22
     seed
    0.21
     Seeds
    0.20
    .seed
    0.19
    _seed
    0.18
    seed
    0.18
    æĴŃç§į
    0.17
    ç±½
    0.17
    (seed
    0.17
    Activations Density 0.095%

    No Known Activations