© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16746
    Prev
    Next
    INDEX
    Explanations

    push back

    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
    PRESS
    -0.12
    lys
    -0.12
     Bare
    -0.11
    oller
    -0.11
    lyn
    -0.11
    jay
    -0.11
    íĻĺ
    -0.10
    <thead
    -0.10
    auc
    -0.10
     fancy
    -0.10
    POSITIVE LOGITS
    down
    0.14
    back
    0.12
     aside
    0.12
    edback
    0.12
    _back
    0.12
     forward
    0.11
    (es
    0.11
     down
    0.11
    -down
    0.11
    /p
    0.11
    Activations Density 0.034%

    No Known Activations