© 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. 111969
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by questions or phrases

    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
     dear
    -0.11
     precious
    -0.09
     gentlemen
    -0.09
    hr
    -0.08
     brill
    -0.08
     Bert
    -0.08
    ess
    -0.08
     ar
    -0.08
    !
    -0.07
    awns
    -0.07
    POSITIVE LOGITS
     Furn
    0.10
    sie
    0.10
    xDA
    0.10
    wards
    0.10
    iete
    0.09
    Lie
    0.09
     Petr
    0.09
    ()=>
    0.09
    ".↵↵↵↵
    0.09
    iline
    0.09
    Activations Density 0.020%

    No Known Activations