© 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. 30154
    Prev
    Next
    INDEX
    Explanations

    childhood stories and simple descriptions

    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
     damn
    -0.19
    damn
    -0.15
     frankly
    -0.15
     damned
    -0.15
     fucking
    -0.15
    Damn
    -0.14
     Damn
    -0.14
     hell
    -0.14
     fuck
    -0.12
     Fuck
    -0.12
    POSITIVE LOGITS
     mommy
    0.21
     yummy
    0.16
     Daddy
    0.15
     scary
    0.15
     lots
    0.14
     silly
    0.13
     Lots
    0.13
     daddy
    0.13
    lots
    0.13
    Lots
    0.12
    Activations Density 0.222%

    No Known Activations