© 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. 25621
    Prev
    Next
    INDEX
    Explanations

    questions, suggestions, or ideas

    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
     debacle
    -0.09
     myself
    -0.08
    eres
    -0.08
     practically
    -0.08
     Glory
    -0.07
     Fame
    -0.07
    ubb
    -0.07
    ropy
    -0.07
     glory
    -0.07
    à¸ĵ
    -0.07
    POSITIVE LOGITS
     any
    0.15
    -any
    0.14
    (any
    0.14
     spare
    0.14
     objections
    0.13
     favorite
    0.13
     Suggestions
    0.12
    rium
    0.12
    favorite
    0.12
     contrario
    0.12
    Activations Density 0.020%

    No Known Activations