© 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. 32466
    Prev
    Next
    INDEX
    Explanations

    claim

    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
    lc
    -0.10
    ical
    -0.10
    eenth
    -0.09
    rote
    -0.09
    rog
    -0.09
    ifer
    -0.09
     cav
    -0.09
     Programmer
    -0.09
    ams
    -0.09
     Wishlist
    -0.09
    POSITIVE LOGITS
    ants
    0.18
    ant
    0.15
    aint
    0.13
    .Claims
    0.12
    ancy
    0.12
    ANTS
    0.12
     claim
    0.11
    ations
    0.10
    claims
    0.10
     Antarctic
    0.10
    Activations Density 0.064%

    No Known Activations