© 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. 46730
    Prev
    Next
    INDEX
    Explanations

    sides and corners

    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
    iego
    -0.09
    loo
    -0.09
    {/*
    -0.09
     Holding
    -0.09
    enz
    -0.09
     Tus
    -0.09
    elah
    -0.08
     Cand
    -0.08
     jealous
    -0.08
     lever
    -0.08
    POSITIVE LOGITS
     corner
    0.20
     corners
    0.16
    corner
    0.15
    Corner
    0.12
     edge
    0.12
    -corner
    0.12
     Corner
    0.11
     onstage
    0.11
     quarter
    0.10
     side
    0.10
    Activations Density 0.157%

    No Known Activations