© 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. 16565
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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
    abi
    -0.09
     loose
    -0.09
    ,)
    -0.08
    ivan
    -0.08
    [
    -0.08
     Bau
    -0.08
    .-
    -0.08
    enk
    -0.08
     bypass
    -0.08
    ette
    -0.08
    POSITIVE LOGITS
     “âĢ¦
    0.11
     "...
    0.10
    cef
    0.09
    indow
    0.09
     "..
    0.09
    "+↵
    0.09
     ""↵↵
    0.09
     sterling
    0.09
     Laur
    0.08
     pole
    0.08
    Activations Density 0.029%

    No Known Activations