© 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. 47637
    Prev
    Next
    INDEX
    Explanations

    Jeffrey or Rey followed by a name

    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
    icity
    -0.11
    ic
    -0.11
    roc
    -0.10
     ple
    -0.10
     irrig
    -0.10
    eyes
    -0.10
    leton
    -0.10
    ness
    -0.10
     conjug
    -0.09
    nock
    -0.09
    POSITIVE LOGITS
     Lumpur
    0.09
    anzi
    0.09
     Ariel
    0.09
    wb
    0.09
    erver
    0.08
     côté
    0.08
     waged
    0.08
     melted
    0.08
    Anchor
    0.08
     Joshua
    0.07
    Activations Density 0.017%

    No Known Activations