© 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. 17240
    Prev
    Next
    INDEX
    Explanations

    Gray followed by names or types

    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
    s
    -0.11
    rick
    -0.08
    erin
    -0.08
    silver
    -0.07
     Gree
    -0.07
    sch
    -0.07
    eds
    -0.07
    sed
    -0.07
     funny
    -0.07
    ized
    -0.07
    POSITIVE LOGITS
    son
    0.13
    don
    0.12
    mere
    0.12
    .githubusercontent
    0.12
    SON
    0.12
    gfx
    0.11
    thresh
    0.11
    bill
    0.10
     advertised
    0.10
     completo
    0.10
    Activations Density 0.008%

    No Known Activations