© 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. 111902
    Prev
    Next
    INDEX
    Explanations

    being mentioned or involved

    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
    adesh
    -0.11
     defin
    -0.09
    ĸī
    -0.09
    /at
    -0.08
    374
    -0.08
     Dew
    -0.08
    sembling
    -0.08
    Ù
    -0.08
     fac
    -0.08
    phot
    -0.08
    POSITIVE LOGITS
     being
    0.42
     becoming
    0.30
    being
    0.28
     getting
    0.27
     Being
    0.23
    Being
    0.22
     gaining
    0.22
     having
    0.20
     staying
    0.20
     taking
    0.19
    Activations Density 0.426%

    No Known Activations