© 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. 14699
    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
     Chase
    -0.09
    DW
    -0.08
     Sv
    -0.08
     Nu
    -0.08
    lop
    -0.08
     Trout
    -0.08
     jumps
    -0.08
     traps
    -0.08
     Polic
    -0.08
    MD
    -0.08
    POSITIVE LOGITS
     Designs
    0.09
    arde
    0.09
    ODO
    0.09
    ,âĢ¦
    0.09
    JO
    0.09
    ç¢
    0.09
    /address
    0.09
     brunette
    0.09
    ially
    0.09
    itra
    0.09
    Activations Density 0.000%

    No Known Activations