© 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. 17661
    Prev
    Next
    INDEX
    Explanations

    atop higher surfaces

    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
     cane
    -0.11
     undercut
    -0.10
     underground
    -0.10
    olon
    -0.08
     Pax
    -0.08
     reel
    -0.08
    SCI
    -0.08
     Til
    -0.08
    oin
    -0.08
    inue
    -0.08
    POSITIVE LOGITS
     atop
    0.26
     perch
    0.17
     rooft
    0.16
     climbing
    0.15
     rooftop
    0.14
     precarious
    0.14
     climbed
    0.14
     prec
    0.14
     suspended
    0.14
     climb
    0.14
    Activations Density 0.068%

    No Known Activations