© 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. 116757
    Prev
    Next
    INDEX
    Explanations

    seen or saw followed by a noun/adjective

    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
    lian
    -0.09
    ãĥ¼ãĥĪ
    -0.08
    ikan
    -0.08
     Eag
    -0.08
     fus
    -0.08
     miniature
    -0.08
    ito
    -0.08
    casts
    -0.08
     stance
    -0.08
    ?}",
    -0.08
    POSITIVE LOGITS
     success
    0.13
     daylight
    0.12
     fruition
    0.12
    rim
    0.11
     completion
    0.10
    ode
    0.10
     sunrise
    0.10
     revenues
    0.10
     sunlight
    0.10
     benefit
    0.10
    Activations Density 0.088%

    No Known Activations