© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 7532
    Prev
    Next
    INDEX
    Explanations

    oval and rectangular shapes

    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
     spherical
    -0.13
     circular
    -0.12
     Circular
    -0.12
     radial
    -0.11
     Sphere
    -0.11
     Circle
    -0.10
     round
    -0.10
     circle
    -0.10
    _circle
    -0.10
    Circle
    -0.10
    POSITIVE LOGITS
    -shaped
    0.23
     shaped
    0.19
     shape
    0.13
     shaping
    0.12
     prism
    0.11
    -Sh
    0.11
    -section
    0.11
    oit
    0.11
     Shape
    0.10
    /disc
    0.10
    Activations Density 0.132%

    No Known Activations