© 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. 26701
    Prev
    Next
    INDEX
    Explanations

    each other

    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
    isky
    -0.09
    uned
    -0.09
    loc
    -0.09
     Rac
    -0.09
     Mad
    -0.09
    407
    -0.09
    ropol
    -0.08
     indexed
    -0.08
    imers
    -0.08
     Pol
    -0.08
    POSITIVE LOGITS
     others
    0.31
    others
    0.27
     Others
    0.25
    Others
    0.23
     respective
    0.23
     another
    0.21
     respectively
    0.20
     other
    0.18
     дÑĢÑĥг
    0.18
    another
    0.17
    Activations Density 0.089%

    No Known Activations