© 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. 25724
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings in URLs or ids

    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
     Integrity
    -0.09
     integral
    -0.09
     cardinal
    -0.09
     incidental
    -0.09
    .ease
    -0.08
    llib
    -0.08
     pend
    -0.08
     wax
    -0.08
     mixed
    -0.08
     synchron
    -0.08
    POSITIVE LOGITS
    _rw
    0.11
    /mat
    0.10
    ijo
    0.10
    лаÑĤ
    0.10
    forme
    0.10
     да
    0.10
     Shields
    0.10
     Benton
    0.09
     Kit
    0.09
     Pot
    0.09
    Activations Density 0.066%

    No Known Activations