© 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. 112234
    Prev
    Next
    INDEX
    Explanations

    scores and dates

    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
     Garland
    -0.11
     gall
    -0.10
    oplast
    -0.09
    aura
    -0.09
    urch
    -0.09
     ALTER
    -0.09
     enriched
    -0.09
     RELATED
    -0.09
     Kelley
    -0.09
    ooks
    -0.09
    POSITIVE LOGITS
     mediocre
    0.09
     weakest
    0.09
    rog
    0.09
     scor
    0.09
    alen
    0.09
     variables
    0.09
    <|fim_middle|>
    0.09
     clen
    0.08
    lest
    0.08
     lest
    0.08
    Activations Density 0.062%

    No Known Activations