© 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. 16641
    Prev
    Next
    INDEX
    Explanations

    barred brown back

    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
    udi
    -0.11
    fib
    -0.11
     Fibonacci
    -0.10
     Lone
    -0.10
     Fran
    -0.10
     fle
    -0.09
    iment
    -0.09
     accidental
    -0.09
     unknown
    -0.09
     Fib
    -0.09
    POSITIVE LOGITS
    -faced
    0.15
     face
    0.13
    -face
    0.12
     faces
    0.11
    face
    0.11
    -sk
    0.10
    skins
    0.10
     FACE
    0.10
    Face
    0.10
    faces
    0.10
    Activations Density 0.002%

    No Known Activations