© 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. 115808
    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
     trails
    -0.11
     Trail
    -0.09
     whip
    -0.09
     Yates
    -0.09
    Trail
    -0.09
     Poverty
    -0.09
    _PRI
    -0.09
     trail
    -0.09
    nya
    -0.08
    [:,:
    -0.08
    POSITIVE LOGITS
     carn
    0.13
     simultaneously
    0.11
     simultaneous
    0.10
     instant
    0.10
    prof
    0.09
     eup
    0.09
    steen
    0.09
    wend
    0.09
     eer
    0.09
    anan
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.