© 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. 91677
    Prev
    Next
    INDEX
    Explanations

    left behind

    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
    tridge
    -0.09
    esta
    -0.08
    roi
    -0.08
    love
    -0.08
    723
    -0.08
     Tage
    -0.08
    ror
    -0.08
     Wool
    -0.07
    Wo
    -0.07
     departure
    -0.07
    POSITIVE LOGITS
     behind
    0.15
     aside
    0.14
     Behind
    0.12
    aside
    0.12
     intact
    0.11
     untouched
    0.11
    _beh
    0.11
     unanswered
    0.11
    ucs
    0.11
    bih
    0.10
    Activations Density 0.036%

    No Known Activations