© 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. 17533
    Prev
    Next
    INDEX
    Explanations

    inside locations

    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
    rex
    -0.13
    ivor
    -0.11
    ivate
    -0.11
    nt
    -0.11
    nc
    -0.10
    ings
    -0.10
    иÑĦ
    -0.09
     hor
    -0.09
    marks
    -0.09
    phant
    -0.09
    POSITIVE LOGITS
    /out
    0.22
    halb
    0.14
    -out
    0.13
    /on
    0.13
    -Out
    0.12
    bounds
    0.11
    -outs
    0.10
    uder
    0.10
    /up
    0.10
    /ext
    0.10
    Activations Density 0.041%

    No Known Activations