© 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. 46524
    Prev
    Next
    INDEX
    Explanations

    'quoted text'

    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
     '
    -0.14
     ‘
    -0.13
     «
    -0.10
     Daw
    -0.09
     Marg
    -0.09
    eler
    -0.09
     Katz
    -0.09
    -at
    -0.08
     Wol
    -0.08
     wol
    -0.08
    POSITIVE LOGITS
    '/
    0.11
    "/
    0.11
    'gc
    0.10
    ’
    0.10
    lio
    0.10
     Airways
    0.10
     Ment
    0.10
    ottie
    0.10
    âĢļ
    0.10
    .TH
    0.09
    Activations Density 0.939%

    No Known Activations