© 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. 89108
    Prev
    Next
    INDEX
    Explanations

    links, URLs, paths

    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
    ako
    -0.09
     connected
    -0.08
    unge
    -0.08
     Wag
    -0.08
     aged
    -0.08
     Aub
    -0.08
    bek
    -0.08
    åĬŁ
    -0.08
    chants
    -0.08
     stiff
    -0.08
    POSITIVE LOGITS
    http
    0.19
    'https
    0.19
    "http
    0.19
    https
    0.18
    =https
    0.18
     http
    0.17
    "https
    0.17
    'http
    0.16
    ://
    0.16
     https
    0.16
    Activations Density 1.742%

    No Known Activations