© 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. 115761
    Prev
    Next
    INDEX
    Explanations

    community events and items

    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
     sting
    -0.07
    gre
    -0.07
    she
    -0.07
     spect
    -0.07
     Zah
    -0.07
     Rear
    -0.07
     McMahon
    -0.07
    imb
    -0.07
    ety
    -0.07
    She
    -0.07
    POSITIVE LOGITS
     desn
    0.11
    pard
    0.11
     =================================================================
    0.11
    /ref
    0.11
    [âĢ¦
    0.11
     mur
    0.11
    uld
    0.10
     phased
    0.10
     forged
    0.10
    yal
    0.10
    Activations Density 0.055%

    No Known Activations