© 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. 47148
    Prev
    Next
    INDEX
    Explanations

    version numbers or dates

    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
     dep
    -0.09
     sav
    -0.09
     Bang
    -0.08
    [d
    -0.08
     navig
    -0.08
     sl
    -0.08
    GBP
    -0.08
    201
    -0.08
     unf
    -0.08
     Missing
    -0.08
    POSITIVE LOGITS
    01
    0.11
    02
    0.09
     tou
    0.09
     reputed
    0.09
    06
    0.09
    oca
    0.09
    07
    0.09
    05
    0.08
     crisis
    0.08
    inki
    0.08
    Activations Density 0.004%

    No Known Activations