© 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. 50422
    Prev
    Next
    INDEX
    Explanations

    requires or necessary to

    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
     Claus
    -0.10
    oso
    -0.10
    /request
    -0.10
     Jeb
    -0.10
     lest
    -0.09
    orsk
    -0.09
     Laz
    -0.09
     hi
    -0.09
    ervo
    -0.09
    .dart
    -0.09
    POSITIVE LOGITS
    æī
    0.09
     pot
    0.09
    zer
    0.09
     Kro
    0.09
     cupid
    0.09
     accompl
    0.09
     accomplish
    0.09
    igs
    0.09
     if
    0.08
    cope
    0.08
    Activations Density 0.188%

    No Known Activations