© 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. 90211
    Prev
    Next
    INDEX
    Explanations

    the reason

    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
     reluctant
    -0.08
     extremes
    -0.07
     own
    -0.07
     purely
    -0.07
     midst
    -0.07
     rápido
    -0.07
    Ñĭваем
    -0.07
    езÑĥлÑĮÑĤ
    -0.06
     pinch
    -0.06
    avar
    -0.06
    POSITIVE LOGITS
     reason
    0.59
    reason
    0.39
     Reason
    0.34
    Reason
    0.30
     reasons
    0.27
     only
    0.26
    (reason
    0.24
     raison
    0.24
    _reason
    0.24
     ONLY
    0.24
    Activations Density 0.347%

    No Known Activations