© 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. 29055
    Prev
    Next
    INDEX
    Explanations

    stationary, connected, external, powered, wired

    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
    sparse
    -0.10
     sparse
    -0.09
     Sparse
    -0.08
    fleet
    -0.08
     Package
    -0.08
    -blind
    -0.08
     Bren
    -0.08
     defective
    -0.08
     Overse
    -0.08
     popular
    -0.08
    POSITIVE LOGITS
     tether
    0.18
     cumbersome
    0.16
     stationary
    0.15
     externally
    0.14
    -connected
    0.14
     connected
    0.14
     bulky
    0.14
     external
    0.13
    -powered
    0.13
     powered
    0.13
    Activations Density 0.314%

    No Known Activations