© 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. 46820
    Prev
    Next
    INDEX
    Explanations

    maze, labyrinth, winding paths, network

    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
     decency
    -0.09
    ringe
    -0.09
     FU
    -0.08
     widen
    -0.08
     ann
    -0.08
     Hover
    -0.08
     Chun
    -0.08
    AU
    -0.08
    tru
    -0.08
     payloads
    -0.08
    POSITIVE LOGITS
     maze
    0.25
     labyrinth
    0.22
    maze
    0.21
     Maze
    0.20
     confusing
    0.20
     twists
    0.20
     twisting
    0.18
     intricate
    0.18
     paths
    0.18
     interconnected
    0.17
    Activations Density 0.227%

    No Known Activations