© 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. 27599
    Prev
    Next
    INDEX
    Explanations

    counterfeit, fake, authentic

    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
    rich
    -0.11
     advant
    -0.10
     flaw
    -0.10
     reconsider
    -0.10
    utom
    -0.10
    ilib
    -0.10
     ters
    -0.10
     toll
    -0.10
     anonym
    -0.10
    ailable
    -0.09
    POSITIVE LOGITS
     fake
    0.36
     counterfeit
    0.32
     authenticity
    0.31
     Fake
    0.31
    Fake
    0.29
     authentic
    0.28
     Authentic
    0.28
    fake
    0.27
     impost
    0.25
     fraudulent
    0.24
    Activations Density 0.184%

    No Known Activations