© 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. 116476
    Prev
    Next
    INDEX
    Explanations

    reason or explanation for something

    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
    oda
    -0.07
    oya
    -0.07
     Mend
    -0.07
     untrue
    -0.07
     erroneous
    -0.06
     configur
    -0.06
     dwelling
    -0.06
     frankly
    -0.06
     detailing
    -0.06
     paradox
    -0.06
    POSITIVE LOGITS
     reasons
    0.44
     reason
    0.43
     Reasons
    0.38
     justification
    0.36
    Reason
    0.35
    reason
    0.35
     rationale
    0.31
     justified
    0.31
     justify
    0.30
     Reason
    0.30
    Activations Density 0.136%

    No Known Activations