© 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. 6763
    Prev
    Next
    INDEX
    Explanations

    pushing or depressing

    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
    zi
    -0.10
     Captain
    -0.10
    uset
    -0.10
     Canal
    -0.10
     corre
    -0.10
     ZZ
    -0.09
     nasty
    -0.09
    wap
    -0.09
    swap
    -0.09
    orre
    -0.09
    POSITIVE LOGITS
     pressure
    0.18
     pushing
    0.17
     push
    0.17
    _push
    0.15
     Push
    0.15
     PUSH
    0.15
     lever
    0.15
     pushes
    0.15
    pressure
    0.15
     pressing
    0.14
    Activations Density 0.055%

    No Known Activations