© 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. 30821
    Prev
    Next
    INDEX
    Explanations

    counts of items or probabilities

    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
    isé
    -0.10
     Lair
    -0.09
     Zug
    -0.09
    ilon
    -0.09
     Pais
    -0.09
     Barg
    -0.09
     demean
    -0.09
     pleasantly
    -0.09
    posit
    -0.08
     Duo
    -0.08
    POSITIVE LOGITS
    urr
    0.09
     nast
    0.08
    undef
    0.08
     rest
    0.08
     uncert
    0.08
    /or
    0.08
    atars
    0.08
    olib
    0.08
     lange
    0.08
    bard
    0.08
    Activations Density 0.753%

    No Known Activations