© 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. 33065
    Prev
    Next
    INDEX
    Explanations

    demanding answers or action

    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
     Nass
    -0.12
     gracious
    -0.10
     subur
    -0.10
     Greenwood
    -0.10
     slightly
    -0.10
     syn
    -0.10
     pleas
    -0.10
     request
    -0.10
    resolved
    -0.10
    esen
    -0.10
    POSITIVE LOGITS
     immediate
    0.14
     demanded
    0.13
     attention
    0.11
     immediately
    0.11
     answers
    0.11
     Immediate
    0.11
     recognition
    0.11
     explanation
    0.11
     Attention
    0.11
     accountability
    0.10
    Activations Density 0.026%

    No Known Activations