© 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. 114033
    Prev
    Next
    INDEX
    Explanations

    code or documentation sections

    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
    cline
    -0.09
     Chun
    -0.09
    webs
    -0.09
    nds
    -0.09
     Ut
    -0.09
    unker
    -0.09
     Tah
    -0.09
    uzzi
    -0.09
    ellas
    -0.08
     Glo
    -0.08
    POSITIVE LOGITS
    onis
    0.09
    zel
    0.09
     fascination
    0.09
    (Size
    0.09
     Fasc
    0.09
     alternate
    0.09
     Hobby
    0.09
     Alternate
    0.09
    onz
    0.08
     aids
    0.08
    Activations Density 0.001%

    No Known Activations