© 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. 6713
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    zas
    -0.08
    ce
    -0.08
     squat
    -0.08
     Fowler
    -0.08
    836
    -0.08
    owy
    -0.07
    owe
    -0.07
     Humph
    -0.07
     Holt
    -0.07
     cleaned
    -0.07
    POSITIVE LOGITS
    -license
    0.12
    dens
    0.11
     unprotected
    0.10
     skulls
    0.10
    ings
    0.10
    ought
    0.10
    kah
    0.10
    kop
    0.10
    itest
    0.09
     lets
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.