© 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. 29788
    Prev
    Next
    INDEX
    Explanations

    check out or check the

    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
     Emanuel
    -0.12
     Tester
    -0.11
     Airways
    -0.11
    AUT
    -0.11
     clam
    -0.11
    _chk
    -0.11
     eminent
    -0.11
     wchar
    -0.10
     hatch
    -0.10
     Crest
    -0.10
    POSITIVE LOGITS
    ered
    0.13
    -out
    0.12
     out
    0.12
    mate
    0.12
    lists
    0.11
    outs
    0.11
    icles
    0.11
    mark
    0.10
    icle
    0.10
    up
    0.09
    Activations Density 0.036%

    No Known Activations