© 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. 32847
    Prev
    Next
    INDEX
    Explanations

    parentheses, commas, or dashes

    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
    Č↵
    -0.09
     Reviewed
    -0.09
    enic
    -0.09
    /mat
    -0.09
     Ung
    -0.09
    emo
    -0.09
     interes
    -0.08
    ewed
    -0.08
    /card
    -0.08
    conte
    -0.08
    POSITIVE LOGITS
     obviously
    0.50
     obvious
    0.49
    du
    0.46
     du
    0.45
     Obviously
    0.40
    Obviously
    0.37
     DU
    0.34
    -du
    0.33
    DU
    0.32
     Du
    0.29
    Activations Density 0.297%

    No Known Activations