© 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. 5960
    Prev
    Next
    INDEX
    Explanations

    constant growth, velocity, frequency, light, regions

    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
    ison
    -0.11
    iena
    -0.09
    ahoma
    -0.09
    ìĦľ
    -0.09
    :ss
    -0.09
     sudden
    -0.09
    ugin
    -0.09
    izon
    -0.08
     convin
    -0.08
     gusto
    -0.08
    POSITIVE LOGITS
     barrage
    0.12
     vigil
    0.12
     companion
    0.12
    ellation
    0.11
    ople
    0.11
    eel
    0.11
    cies
    0.11
    LY
    0.11
     companions
    0.11
    ipation
    0.10
    Activations Density 0.070%

    No Known Activations