© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90338
    Prev
    Next
    INDEX
    Explanations

    separators or special characters

    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
     )))
    -0.10
     Hus
    -0.10
    isser
    -0.09
     Dude
    -0.09
    лав
    -0.08
     Mundo
    -0.08
    /logging
    -0.08
     beau
    -0.08
    (END
    -0.08
     Benson
    -0.08
    POSITIVE LOGITS
     unf
    0.12
    fdb
    0.11
    (click
    0.10
     Castillo
    0.10
    asca
    0.10
    404
    0.09
    Âł
    0.09
    fan
    0.09
    ijk
    0.09
    fil
    0.09
    Activations Density 0.025%

    No Known Activations