© 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. 88270
    Prev
    Next
    INDEX
    Explanations

    .fi file extensions

    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
    rouch
    -0.13
    opher
    -0.12
    phony
    -0.11
    usk
    -0.10
     exper
    -0.10
    rikes
    -0.10
     ung
    -0.10
    uso
    -0.10
    atos
    -0.10
    itect
    -0.10
    POSITIVE LOGITS
    qh
    0.11
    NAL
    0.11
    orent
    0.10
    ery
    0.10
     Flat
    0.10
     rst
    0.09
    Fo
    0.09
    end
    0.09
    rst
    0.09
     Gerald
    0.09
    Activations Density 0.009%

    No Known Activations