© 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. 15300
    Prev
    Next
    INDEX
    Explanations

    Senior Lecturer

    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
     Banc
    -0.09
     greens
    -0.08
     Fauc
    -0.08
     cig
    -0.07
     Â
    -0.07
    Â
    -0.07
    /port
    -0.07
     Torrent
    -0.07
    ÂĴ
    -0.07
     [.
    -0.07
    POSITIVE LOGITS
     LH
    0.15
     Valentine
    0.14
     honey
    0.12
     Shipping
    0.12
    (L
    0.12
     LD
    0.12
     Honey
    0.12
     Ship
    0.12
    .rl
    0.12
     LR
    0.12
    Activations Density 0.005%

    No Known Activations