© 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. 26540
    Prev
    Next
    INDEX
    Explanations

    inventions and relation to others

    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
     indoors
    -0.16
     room
    -0.16
     Ceiling
    -0.15
     indoor
    -0.15
     upstairs
    -0.15
     ceiling
    -0.14
     door
    -0.14
     Room
    -0.13
     rooms
    -0.13
     Rooms
    -0.12
    POSITIVE LOGITS
     neighbouring
    0.14
     neighboring
    0.13
     bart
    0.12
     bartender
    0.11
    ensa
    0.10
     neighbour
    0.10
     Rede
    0.10
     parallel
    0.10
    bart
    0.10
     Bart
    0.10
    Activations Density 0.262%

    No Known Activations