© 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. 29820
    Prev
    Next
    INDEX
    Explanations

    sequences or after punctuation

    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
     Ones
    -0.11
    awe
    -0.11
    ritz
    -0.11
    etak
    -0.10
    à¸ģาร
    -0.10
    aban
    -0.10
     Leads
    -0.10
    este
    -0.10
    arella
    -0.10
     quanto
    -0.09
    POSITIVE LOGITS
     a
    0.18
     an
    0.18
     which
    0.14
    an
    0.13
     whose
    0.12
    which
    0.11
    ä¸Ģ个
    0.11
    a
    0.10
     arguably
    0.09
     aka
    0.09
    Activations Density 0.611%

    No Known Activations