© 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. 31477
    Prev
    Next
    INDEX
    Explanations

    integrates, sport, extrusion, salsa, harvey, & me

    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
     Accum
    -0.10
     âĢİ
    -0.09
    clin
    -0.09
     accumulator
    -0.09
     fleeting
    -0.08
    ensch
    -0.08
    Č↵
    -0.08
     Shoe
    -0.08
    å¡
    -0.08
     devour
    -0.08
    POSITIVE LOGITS
    oha
    0.12
     illicit
    0.11
     anytime
    0.11
     illegal
    0.10
    ennen
    0.10
     Howell
    0.10
     undert
    0.10
    Illegal
    0.09
     inherently
    0.09
     undertake
    0.09
    Activations Density 0.001%

    No Known Activations