© 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. 47921
    Prev
    Next
    INDEX
    Explanations

    download files

    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
    well
    -0.10
    igg
    -0.10
    -cols
    -0.10
     Mig
    -0.10
     biscuits
    -0.10
    thal
    -0.10
    ych
    -0.10
    cit
    -0.10
    sert
    -0.10
    ftime
    -0.10
    POSITIVE LOGITS
     onto
    0.22
    /stream
    0.20
    /upload
    0.15
    /print
    0.15
    onto
    0.15
    /uploads
    0.13
    /trans
    0.12
    /view
    0.12
     gratuito
    0.11
    /download
    0.11
    Activations Density 0.111%

    No Known Activations