© 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. 26045
    Prev
    Next
    INDEX
    Explanations

    movement during

    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
     daytime
    -0.09
     arrangements
    -0.08
     arrangement
    -0.07
     Tob
    -0.07
     gulp
    -0.07
    atti
    -0.07
     ruth
    -0.07
     stret
    -0.07
     claw
    -0.07
     arrang
    -0.06
    POSITIVE LOGITS
     sway
    0.15
     hips
    0.14
     planted
    0.12
     rhythm
    0.12
    sid
    0.12
    zag
    0.12
    ala
    0.11
    afi
    0.11
     seated
    0.11
    antal
    0.11
    Activations Density 0.013%

    No Known Activations