© 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. 3004
    Prev
    Next
    INDEX
    Explanations

    nitrogen fixation

    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
    模æĭŁ
    -0.09
    羸
    -0.08
    ãģ®ãģĮ
    -0.08
     eviction
    -0.08
    .bid
    -0.08
    éĤ¸
    -0.08
    _lengths
    -0.08
    模仿
    -0.07
    åıĹçIJĨ
    -0.07
     lengths
    -0.07
    POSITIVE LOGITS
    æ°®
    0.13
     nitrogen
    0.11
    illin
    0.10
    åİĭåĬĽ
    0.10
    -lang
    0.10
    spell
    0.09
    ASC
    0.09
     ÑĤÑĥ
    0.09
    procs
    0.09
    éĥİ
    0.09
    Activations Density 0.041%

    No Known Activations