© 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. 49249
    Prev
    Next
    INDEX
    Explanations

    overhead, ambient, ceiling lighting

    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
     Contacts
    -0.10
    bben
    -0.09
    gmail
    -0.09
    erval
    -0.09
    imei
    -0.09
    /Dk
    -0.09
     Bradford
    -0.09
     explos
    -0.09
     boils
    -0.09
    imore
    -0.09
    POSITIVE LOGITS
     overhead
    0.13
     casc
    0.12
     whisper
    0.12
     muted
    0.11
     ceiling
    0.11
     accents
    0.11
     ceilings
    0.11
     ambient
    0.11
     antique
    0.10
     minimal
    0.10
    Activations Density 0.001%

    No Known Activations