© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113201
    Prev
    Next
    INDEX
    Explanations

    work in progress

    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
    ungle
    -0.10
     Lad
    -0.10
     Horton
    -0.09
     interpolation
    -0.09
    imos
    -0.09
    ointments
    -0.09
    dess
    -0.09
    unte
    -0.09
     Hayden
    -0.09
     ÑĩÑĤ
    -0.09
    POSITIVE LOGITS
    able
    0.11
     vice
    0.11
     prox
    0.10
    caf
    0.10
     factual
    0.09
     scrimmage
    0.08
    hands
    0.08
    bench
    0.08
    ably
    0.08
     bench
    0.08
    Activations Density 0.014%

    No Known Activations