© 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. 5157
    Prev
    Next
    INDEX
    Explanations

    hard to find

    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
     safely
    -0.11
    -ton
    -0.10
     tact
    -0.09
     schw
    -0.09
     ton
    -0.09
     delic
    -0.09
     dare
    -0.09
     autonom
    -0.09
     bib
    -0.08
    nth
    -0.08
    POSITIVE LOGITS
     distinguish
    0.12
     admitting
    0.11
     admit
    0.10
     miss
    0.10
     mistaken
    0.10
     believe
    0.10
     Resist
    0.10
     admission
    0.10
     perch
    0.09
     Lau
    0.09
    Activations Density 0.010%

    No Known Activations