© 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. 49977
    Prev
    Next
    INDEX
    Explanations

    names following a comma

    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
     ingr
    -0.10
    -CS
    -0.09
    ...)
    -0.09
     Fle
    -0.08
     Boys
    -0.08
    leans
    -0.08
    -Un
    -0.08
    -Am
    -0.08
     CHECK
    -0.07
    inq
    -0.07
    POSITIVE LOGITS
     namely
    0.19
     which
    0.16
     whose
    0.15
    whose
    0.15
    which
    0.15
     nicknamed
    0.13
     albeit
    0.13
     коÑĤоÑĢÑĭй
    0.12
     conveniently
    0.11
     viz
    0.11
    Activations Density 0.240%

    No Known Activations