© 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. 88519
    Prev
    Next
    INDEX
    Explanations

    suffix "-al" or "-ial"

    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
    Ī
    -0.10
    orer
    -0.10
     skeleton
    -0.10
    vana
    -0.10
    ertia
    -0.10
    riers
    -0.10
    ioxide
    -0.10
    hare
    -0.09
     Beard
    -0.09
    LOGY
    -0.09
    POSITIVE LOGITS
    itional
    0.17
    otic
    0.17
    atical
    0.16
    imentary
    0.16
    aptic
    0.16
    arial
    0.16
    ìłģ
    0.16
    ical
    0.16
    otional
    0.16
    ytic
    0.16
    Activations Density 0.505%

    No Known Activations