© 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. 32457
    Prev
    Next
    INDEX
    Explanations

    I think

    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
     Hutch
    -0.10
     hel
    -0.10
    ropa
    -0.10
    igu
    -0.10
    htm
    -0.09
     Stern
    -0.09
    enu
    -0.09
     reput
    -0.09
    ignon
    -0.09
    yan
    -0.09
    POSITIVE LOGITS
     appropriate
    0.12
     suitable
    0.10
     Chavez
    0.10
     Mara
    0.09
     pne
    0.09
    arend
    0.09
    atest
    0.09
     correct
    0.09
    Deferred
    0.09
    )section
    0.09
    Activations Density 0.019%

    No Known Activations