© 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. 4632
    Prev
    Next
    INDEX
    Explanations

    license versions and php

    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
     mains
    -0.09
     sok
    -0.09
     Sioux
    -0.09
    letics
    -0.09
    omain
    -0.09
    CHASE
    -0.09
     Cous
    -0.09
    ouston
    -0.08
     aio
    -0.08
     clue
    -0.08
    POSITIVE LOGITS
    (M
    0.24
    |M
    0.21
    "M
    0.20
    [M
    0.19
    =M
    0.18
    ,M
    0.17
     MM
    0.16
    /MM
    0.16
    /M
    0.16
     pym
    0.16
    Activations Density 5.317%

    No Known Activations