© 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. 33327
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     Hubb
    -0.10
    ami
    -0.09
    illas
    -0.09
    orst
    -0.09
    hra
    -0.09
    npos
    -0.08
     Joi
    -0.08
    ник
    -0.08
     bust
    -0.08
     Holl
    -0.08
    POSITIVE LOGITS
     licked
    0.12
    <td
    0.10
    âĢ³
    0.09
    0.09
     undocumented
    0.09
     feliz
    0.08
    0.08
    ï¼ĮãĢĬ
    0.08
    unta
    0.08
     Fort
    0.08
    Activations Density 0.058%

    No Known Activations