© 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. 115313
    Prev
    Next
    INDEX
    Explanations

    fake, amateur, or rescued

    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
     cop
    -0.08
    attery
    -0.07
    exual
    -0.06
     empt
    -0.06
    &e
    -0.06
     racket
    -0.06
     Kar
    -0.06
     Manus
    -0.06
     LSD
    -0.06
     butterflies
    -0.06
    POSITIVE LOGITS
     Fake
    0.12
     LIABILITY
    0.12
     fake
    0.10
     Amateur
    0.10
    inh
    0.10
    inia
    0.10
     Vintage
    0.10
     incons
    0.10
     rescued
    0.10
     amateur
    0.10
    Activations Density 0.074%

    No Known Activations