© 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. 29409
    Prev
    Next
    INDEX
    Explanations

    produced music

    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
    izin
    -0.13
    ucz
    -0.12
     McC
    -0.12
     Sutton
    -0.12
    BBBB
    -0.11
    dorf
    -0.11
    arez
    -0.11
    erras
    -0.11
    DAT
    -0.11
     reform
    -0.11
    POSITIVE LOGITS
     alone
    0.10
     jointly
    0.10
     majority
    0.09
     initial
    0.09
     initially
    0.08
     reap
    0.08
     honors
    0.08
     personally
    0.07
     most
    0.07
     hopeful
    0.07
    Activations Density 0.451%

    No Known Activations