© 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. 46665
    Prev
    Next
    INDEX
    Explanations

    punctuation and question 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
     noting
    -0.11
     Cue
    -0.11
     cue
    -0.10
     TBD
    -0.10
    olders
    -0.10
    -percent
    -0.09
    /about
    -0.09
     shiny
    -0.09
    transparent
    -0.09
    erton
    -0.09
    POSITIVE LOGITS
    CLICK
    0.12
     breakthrough
    0.12
     shocking
    0.12
     FREE
    0.12
     astonishing
    0.11
     hundreds
    0.11
     secret
    0.11
     unbelievable
    0.11
     CLICK
    0.11
    SECRET
    0.11
    Activations Density 0.063%

    No Known Activations