© 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. 111978
    Prev
    Next
    INDEX
    Explanations

    Roman numerals or numbers and letters

    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
    bold
    -0.10
    est
    -0.09
    +-+-
    -0.09
    imal
    -0.09
    angu
    -0.09
    inged
    -0.08
    ../../../
    -0.08
    esan
    -0.08
    lander
    -0.08
     terrible
    -0.08
    POSITIVE LOGITS
    NewLabel
    0.11
    omap
    0.11
    orarily
    0.11
    iasi
    0.10
    ories
    0.10
    orde
    0.10
    .UnitTesting
    0.10
    олÑĮз
    0.10
     quadrant
    0.10
    icion
    0.10
    Activations Density 0.344%

    No Known Activations