© 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. 16092
    Prev
    Next
    INDEX
    Explanations

    bourbon barrel programs

    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
     thumbs
    -0.10
    ogne
    -0.09
     thumb
    -0.09
     Thumb
    -0.09
     exhaust
    -0.09
     olive
    -0.08
     insured
    -0.08
     melted
    -0.08
    mozilla
    -0.08
     worldly
    -0.08
    POSITIVE LOGITS
     cosplay
    0.14
     BDSM
    0.14
     voyeur
    0.14
     hybrids
    0.13
     cuckold
    0.13
     hybrid
    0.12
     cann
    0.11
    vore
    0.11
     nud
    0.11
    -lite
    0.11
    Activations Density 0.059%

    No Known Activations