© 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. 29900
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by punctuation

    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
    #\
    -0.11
     Mari
    -0.11
     expend
    -0.11
    avig
    -0.10
    ior
    -0.10
    COR
    -0.10
     revel
    -0.10
    ...',↵
    -0.10
    arkan
    -0.10
    aeda
    -0.10
    POSITIVE LOGITS
    's
    0.09
     anytime
    0.09
    &apos
    0.09
     Were
    0.09
    *'
    0.08
     quand
    0.08
     &
    0.07
     ('
    0.07
    ’s
    0.07
    èĤ
    0.07
    Activations Density 0.777%

    No Known Activations