© 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. 90429
    Prev
    Next
    INDEX
    Explanations

    pubs, bars, inns, drinking spots

    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
     parking
    -0.10
     airport
    -0.10
     airports
    -0.10
    -driving
    -0.09
     utilise
    -0.09
     freeway
    -0.09
     trespass
    -0.09
     drivers
    -0.09
     bespoke
    -0.09
     Meyer
    -0.09
    POSITIVE LOGITS
     pub
    0.17
     pubs
    0.16
    pub
    0.14
     Pub
    0.14
     PUB
    0.14
     hometown
    0.12
     drinkers
    0.12
     drinking
    0.11
    Pub
    0.11
    .pub
    0.11
    Activations Density 0.090%

    No Known Activations