© 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. 4540
    Prev
    Next
    INDEX
    Explanations

    haircut and salon services

    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
     ob
    -0.10
     feeding
    -0.09
     Ballet
    -0.09
     JE
    -0.08
     APPLE
    -0.08
    ovy
    -0.08
     exped
    -0.08
     Kok
    -0.08
     Scaffold
    -0.08
     Bunny
    -0.08
    POSITIVE LOGITS
     Barber
    0.16
     barber
    0.15
     salon
    0.14
     Clippers
    0.13
     shops
    0.12
    /bar
    0.11
    cuts
    0.11
     shop
    0.11
     stylist
    0.11
     haircut
    0.11
    Activations Density 0.046%

    No Known Activations