© 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. 92210
    Prev
    Next
    INDEX
    Explanations

    Ranger and Service related phrases

    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
    ention
    -0.08
    ocking
    -0.08
     crow
    -0.08
     trips
    -0.08
     coincide
    -0.08
     Crow
    -0.08
     trip
    -0.08
     gl
    -0.08
    iment
    -0.08
    ument
    -0.08
    POSITIVE LOGITS
    uke
    0.11
    lige
    0.11
    hort
    0.10
    avy
    0.10
     salute
    0.10
     Pavel
    0.10
     Boyd
    0.10
    nels
    0.10
     SERIAL
    0.10
     Middleton
    0.10
    Activations Density 0.002%

    No Known Activations