© 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. 49843
    Prev
    Next
    INDEX
    Explanations

    sensory information or overload

    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
    _ctx
    -0.11
     Voll
    -0.10
    odu
    -0.10
    ersh
    -0.10
    utsch
    -0.10
    ooo
    -0.10
    /Common
    -0.10
    ish
    -0.10
     shoe
    -0.09
     unseen
    -0.09
    POSITIVE LOGITS
     overload
    0.12
    -rich
    0.09
     stimulation
    0.09
    es
    0.09
     explodes
    0.08
    abl
    0.08
    abras
    0.08
     overloaded
    0.08
    -friendly
    0.08
    iges
    0.08
    Activations Density 0.013%

    No Known Activations