© 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. 16487
    Prev
    Next
    INDEX
    Explanations

    direction and location indicators

    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
    nik
    -0.11
     STD
    -0.11
     Garrison
    -0.11
    rij
    -0.10
    ;display
    -0.10
    Float
    -0.10
     skipped
    -0.10
    apo
    -0.09
     proto
    -0.09
    nick
    -0.09
    POSITIVE LOGITS
     direction
    0.48
     directions
    0.39
     Direction
    0.38
    direction
    0.38
    Direction
    0.33
     directional
    0.33
    -direction
    0.33
     Directions
    0.31
     towards
    0.29
    (direction
    0.28
    Activations Density 0.189%

    No Known Activations