© 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. 17975
    Prev
    Next
    INDEX
    Explanations

    believe in Jesus

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Zur
    -0.10
     gearing
    -0.10
     taboo
    -0.10
     Cond
    -0.09
     Franken
    -0.09
     Pearce
    -0.09
     JNI
    -0.09
     nood
    -0.08
     cond
    -0.08
     Mod
    -0.08
    POSITIVE LOGITS
     conversion
    0.29
     converted
    0.28
     Converted
    0.26
     converts
    0.25
     convert
    0.25
     conversions
    0.25
     repent
    0.24
     Conversion
    0.24
    Converted
    0.23
     converting
    0.23
    Activations Density 0.299%

    No Known Activations