© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 33393
    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
     Heller
    -0.11
     Dw
    -0.08
     wardrobe
    -0.08
     cigar
    -0.08
    onis
    -0.07
    oker
    -0.07
    pare
    -0.07
     crystall
    -0.07
    UGC
    -0.07
    ury
    -0.07
    POSITIVE LOGITS
     Matthews
    0.11
     movements
    0.10
     Carp
    0.10
     Hits
    0.10
     Opposition
    0.10
     motions
    0.09
     excell
    0.09
     presses
    0.09
     pressed
    0.09
     enthusi
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.