© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13958
    Prev
    Next
    INDEX
    Explanations

    camera and device accessories

    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
    Negative Logits
    .Health
    -0.08
     Aph
    -0.08
     Rodrigo
    -0.08
     Bannon
    -0.08
    /platform
    -0.08
    ))).
    -0.08
     tslint
    -0.07
     Glyph
    -0.07
     ldc
    -0.07
    ernen
    -0.07
    POSITIVE LOGITS
     plugged
    0.11
     Dum
    0.11
     attached
    0.11
     Humph
    0.10
     capable
    0.10
     Elias
    0.10
    heid
    0.10
    ku
    0.10
    é©
    0.10
    /fire
    0.10
    Activations Density 0.010%

    No Known Activations