© 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. 91187
    Prev
    Next
    INDEX
    Explanations

    appearance and features

    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
     lazy
    -0.10
     rhythm
    -0.10
    azzi
    -0.09
     Lazy
    -0.09
    shadow
    -0.09
    bris
    -0.09
    back
    -0.09
     Papa
    -0.09
     extravag
    -0.09
    审
    -0.09
    POSITIVE LOGITS
    -looking
    0.20
     innocent
    0.19
     seeming
    0.16
     innocence
    0.15
     innoc
    0.15
     facade
    0.15
    -faced
    0.14
     appearance
    0.14
     Innoc
    0.14
    -like
    0.13
    Activations Density 0.028%

    No Known Activations