© 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. 17565
    Prev
    Next
    INDEX
    Explanations

    solving equations

    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
    ï¼īãĢģ
    -0.12
     vested
    -0.09
     Stafford
    -0.08
     en
    -0.08
    ian
    -0.08
     Dul
    -0.08
    âĢ¦↵
    -0.08
     tast
    -0.07
    oust
    -0.07
     Dodge
    -0.07
    POSITIVE LOGITS
    <|endoftext|>
    0.15
    .*;↵↵
    0.13
     [])↵↵
    0.13
    âĢ¢↵↵
    0.13
    *↵↵
    0.12
    ..↵↵↵↵
    0.12
     ""↵↵
    0.12
    *)↵↵
    0.12
    ())↵↵
    0.12
    .*;č↵č↵
    0.12
    Activations Density 0.491%

    No Known Activations