© 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. 33440
    Prev
    Next
    INDEX
    Explanations

    being followed by nothing specific

    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
    because
    -0.15
     because
    -0.15
     due
    -0.14
    ecause
    -0.14
     Because
    -0.13
    Because
    -0.12
     owing
    -0.12
    due
    -0.12
    xon
    -0.12
     cuz
    -0.11
    POSITIVE LOGITS
     therefore
    0.17
     erg
    0.13
     means
    0.12
     hence
    0.12
     meaning
    0.12
     quindi
    0.11
     thus
    0.11
    ë¯
    0.11
     Erg
    0.11
     wiÄĻc
    0.11
    Activations Density 0.190%

    No Known Activations