© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7015
    Prev
    Next
    INDEX
    Explanations

    germination seeds

    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
    iku
    -0.11
    ather
    -0.10
    ç«¿
    -0.09
    Buffers
    -0.09
    raq
    -0.09
    æĶ¯
    -0.09
    afort
    -0.09
    icken
    -0.09
    abant
    -0.08
     kicker
    -0.08
    POSITIVE LOGITS
    ç§įåŃIJ
    0.14
    çĿ«æ¯Ľ
    0.10
     seeds
    0.09
    ç§ĥ
    0.09
    解说
    0.09
     Seeds
    0.09
    æķĪ
    0.09
    èĥļ
    0.09
     seed
    0.09
    æĸ°æĹ¶ä»£
    0.09
    Activations Density 0.059%

    No Known Activations