© 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. 33565
    Prev
    Next
    INDEX
    Explanations

    forms encrusting masses

    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
    “But
    -0.15
    "But
    -0.12
     misunderstand
    -0.12
    “Well
    -0.11
     “âĢ¦
    -0.11
     Tone
    -0.10
    //{{
    -0.10
    “And
    -0.10
    abe
    -0.10
    iele
    -0.10
    POSITIVE LOGITS
     Bravo
    0.10
     disgusting
    0.10
     plunge
    0.09
    Nice
    0.09
     reaff
    0.09
     shin
    0.09
     sund
    0.09
     Ready
    0.08
     replen
    0.08
     Tee
    0.08
    Activations Density 0.013%

    No Known Activations