© 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. 25370
    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
    ellas
    -0.09
     Widow
    -0.08
    strap
    -0.08
     dow
    -0.08
     selectively
    -0.08
     unfamiliar
    -0.08
     Swe
    -0.08
    izzo
    -0.08
     Netz
    -0.08
     custom
    -0.08
    POSITIVE LOGITS
     Jong
    0.11
    akin
    0.10
    isin
    0.09
     bitterness
    0.09
     warmth
    0.09
     perverse
    0.09
     gee
    0.09
     stranger
    0.09
    seeing
    0.08
     lighten
    0.08
    Activations Density 0.000%

    No Known Activations