© 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. 6938
    Prev
    Next
    INDEX
    Explanations

    head meta http

    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
     Tango
    -0.13
     tongues
    -0.13
     tongue
    -0.12
     Tud
    -0.12
     VERBOSE
    -0.11
    .setLocation
    -0.11
    -lang
    -0.11
     bartender
    -0.11
     Treasury
    -0.10
    olang
    -0.10
    POSITIVE LOGITS
     DeV
    0.08
     cheeks
    0.08
    igaret
    0.08
    -settings
    0.08
     cheek
    0.08
    ocre
    0.08
    Statics
    0.08
    tc
    0.08
    .criteria
    0.07
    oya
    0.07
    Activations Density 0.041%

    No Known Activations