© 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. 31362
    Prev
    Next
    INDEX
    Explanations

    Before judge, chief

    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
     Chill
    -0.09
    <|fim_suffix|>
    -0.09
    Nm
    -0.09
    [âĢ¦
    -0.09
    /port
    -0.09
     Nom
    -0.09
     Kirk
    -0.08
    ugu
    -0.08
    381
    -0.08
    uml
    -0.08
    POSITIVE LOGITS
     stagger
    0.11
     wound
    0.09
    -"
    0.09
     wildly
    0.09
    :"
    0.09
     anx
    0.09
    .--
    0.09
     Bearing
    0.09
     Levy
    0.08
    nex
    0.08
    Activations Density 0.042%

    No Known Activations