© 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. 115827
    Prev
    Next
    INDEX
    Explanations

    pointing, trigger, wires, extended, side, arising

    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
     Bron
    -0.11
     Cou
    -0.10
    éĢŁ
    -0.10
     Geoff
    -0.10
     oral
    -0.10
    yers
    -0.10
     hail
    -0.10
     Hanna
    -0.10
     recap
    -0.10
     facult
    -0.10
    POSITIVE LOGITS
     flatt
    0.11
     pushing
    0.11
     horizontal
    0.10
     laying
    0.10
     pressing
    0.10
     triangular
    0.10
     pushed
    0.10
     flattened
    0.10
     pressed
    0.09
     concealed
    0.09
    Activations Density 0.015%

    No Known Activations