© 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. 7741
    Prev
    Next
    INDEX
    Explanations

    first time in

    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
     never
    -0.11
    never
    -0.10
    assi
    -0.09
     yearly
    -0.09
     NEVER
    -0.09
     Never
    -0.09
     once
    -0.09
     systematically
    -0.09
    _history
    -0.08
    arro
    -0.08
    POSITIVE LOGITS
     in
    0.10
     Gors
    0.10
    ocz
    0.10
     depuis
    0.10
    cott
    0.09
     Forbidden
    0.09
    ardash
    0.09
     within
    0.09
     Fut
    0.09
     since
    0.09
    Activations Density 0.070%

    No Known Activations