© 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. 28686
    Prev
    Next
    INDEX
    Explanations

    circle and ring 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
     downstairs
    -0.12
     rack
    -0.11
     drawer
    -0.10
     scopes
    -0.10
    Terminal
    -0.10
     pref
    -0.10
     drawers
    -0.10
    stairs
    -0.10
     terminal
    -0.09
     upstairs
    -0.09
    POSITIVE LOGITS
     circle
    0.33
     circumference
    0.33
     ring
    0.31
     circular
    0.29
     Circle
    0.29
     concent
    0.28
     radial
    0.27
     Ring
    0.26
    Circle
    0.25
    _circle
    0.25
    Activations Density 0.673%

    No Known Activations