© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115165
    Prev
    Next
    INDEX
    Explanations

    double / blind / spin / hit / click

    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
    ular
    -0.11
    rap
    -0.10
    ilyn
    -0.10
    agen
    -0.09
    è½
    -0.09
    apesh
    -0.09
    sz
    -0.09
    sel
    -0.09
    adir
    -0.09
    ici
    -0.09
    POSITIVE LOGITS
    .parseDouble
    0.17
    .NaN
    0.14
     entend
    0.14
    .TryParse
    0.12
    /tr
    0.12
    -sided
    0.12
    tte
    0.11
    mint
    0.11
    headers
    0.11
    .Parse
    0.11
    Activations Density 0.029%

    No Known Activations