© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17887
    Prev
    Next
    INDEX
    Explanations

    that which who whose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
    æŃ£åľ¨
    -0.13
    clause
    -0.12
    943
    -0.11
    Č↵
    -0.11
    utton
    -0.11
    ãĤĦ
    -0.11
     ли
    -0.11
    sortable
    -0.11
     nya
    -0.11
    otec
    -0.11
    POSITIVE LOGITS
     that
    0.31
     which
    0.27
     whose
    0.25
    that
    0.23
     who
    0.23
    which
    0.19
     коÑĤоÑĢÑĭй
    0.19
     tat
    0.18
     thats
    0.17
    whose
    0.17
    Activations Density 1.533%

    No Known Activations