© 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. 112406
    Prev
    Next
    INDEX
    Explanations

    question words and informal replies

    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
    +xml
    -0.09
    ;base
    -0.08
    ULE
    -0.08
    786
    -0.08
    :č↵č↵
    -0.08
    oner
    -0.08
     initialise
    -0.08
    ilder
    -0.08
     pis
    -0.08
     Ook
    -0.08
    POSITIVE LOGITS
     tact
    0.11
    apid
    0.11
     dude
    0.10
     bro
    0.10
     rapid
    0.10
     cunning
    0.10
     ima
    0.09
     TORT
    0.09
     Bro
    0.09
     ...↵
    0.09
    Activations Density 0.089%

    No Known Activations