© 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. 47590
    Prev
    Next
    INDEX
    Explanations

    .githubusercontent and .com

    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
    �t
    -0.11
    unu
    -0.10
     smack
    -0.10
     |/
    -0.09
    Outline
    -0.09
    enga
    -0.09
    isy
    -0.09
     VN
    -0.09
     RW
    -0.09
     ratt
    -0.09
    POSITIVE LOGITS
    /browse
    0.10
    olan
    0.09
    -re
    0.08
     spontaneously
    0.08
    à§į
    0.08
    .mybatisplus
    0.08
    esch
    0.08
    olon
    0.08
     ult
    0.08
    PERT
    0.08
    Activations Density 0.377%

    No Known Activations