© 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. 16901
    Prev
    Next
    INDEX
    Explanations

    lists punctuation followed by pronouns or names

    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
     unders
    -0.10
    âĢij
    -0.10
     yesterday
    -0.10
    mmo
    -0.10
     dude
    -0.10
     Hä
    -0.10
    opo
    -0.09
    wow
    -0.09
    wdx
    -0.09
    —it
    -0.09
    POSITIVE LOGITS
     protagon
    0.11
     labelled
    0.10
     unfore
    0.10
     oblivious
    0.10
    cec
    0.10
     alles
    0.09
     preca
    0.09
     tumblr
    0.09
     discovers
    0.09
    opro
    0.09
    Activations Density 0.059%

    No Known Activations