© 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. 88083
    Prev
    Next
    INDEX
    Explanations

    get information or service

    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
     receiving
    -0.11
     adequately
    -0.10
    unny
    -0.10
     received
    -0.10
    enticator
    -0.10
    emm
    -0.09
     Aires
    -0.09
     Bunny
    -0.09
     tipping
    -0.09
    usch
    -0.08
    POSITIVE LOGITS
     happen
    0.11
     from
    0.11
     underway
    0.11
     dia
    0.10
     figured
    0.10
     added
    0.10
     Fig
    0.09
    from
    0.09
     restored
    0.09
     installed
    0.09
    Activations Density 0.136%

    No Known Activations