© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90607
    Prev
    Next
    INDEX
    Explanations

    you followed by a verb

    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
    ñ
    -0.10
    strain
    -0.09
    vang
    -0.09
    slaught
    -0.09
    ?action
    -0.09
    anova
    -0.08
     Grat
    -0.08
     duk
    -0.08
     Fighters
    -0.08
    amd
    -0.08
    POSITIVE LOGITS
     little
    0.13
     r
    0.11
    asin
    0.11
     silly
    0.10
     prospective
    0.10
     mor
    0.10
    ses
    0.10
    raud
    0.09
     piece
    0.09
     termin
    0.09
    Activations Density 0.016%

    No Known Activations