© 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. 50363
    Prev
    Next
    INDEX
    Explanations

    numbers followed by colon

    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
    brook
    -0.08
    -order
    -0.07
    pty
    -0.07
     equally
    -0.07
     HIM
    -0.06
    fleet
    -0.06
     nop
    -0.06
    ogo
    -0.06
    PATH
    -0.06
    angu
    -0.06
    POSITIVE LOGITS
    _rat
    0.12
    isset
    0.11
    usch
    0.11
    /original
    0.11
    usto
    0.11
    inality
    0.11
     familia
    0.11
    opor
    0.11
    0.10
    uttgart
    0.10
    Activations Density 0.036%

    No Known Activations