© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5962
    Prev
    Next
    INDEX
    Explanations

    `[@` citation patterns

    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
     cot
    -0.10
     sometime
    -0.10
    utton
    -0.10
     upstream
    -0.10
     sou
    -0.10
    weit
    -0.10
     Runner
    -0.10
    ï¸
    -0.10
     Sheikh
    -0.10
     recomm
    -0.10
    POSITIVE LOGITS
     tal
    0.08
     Gest
    0.08
    entai
    0.08
     mand
    0.07
     UNIVERS
    0.07
     “âĢ¦
    0.07
    âĢ¦it
    0.07
     bod
    0.07
    reon
    0.07
    ãĢİ
    0.07
    Activations Density 0.066%

    No Known Activations