© 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. 88566
    Prev
    Next
    INDEX
    Explanations

    and/or or import

    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
     Zig
    -0.11
    /we
    -0.11
     Existing
    -0.11
     recess
    -0.11
     existing
    -0.10
     Victory
    -0.10
    igua
    -0.10
     Cel
    -0.10
     Rog
    -0.10
    mux
    -0.09
    POSITIVE LOGITS
    stad
    0.08
    anky
    0.07
    vers
    0.07
    ename
    0.07
     forgot
    0.07
    anning
    0.07
     vs
    0.07
     correcting
    0.07
     Demp
    0.07
     hes
    0.07
    Activations Density 0.004%

    No Known Activations