© 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. 113502
    Prev
    Next
    INDEX
    Explanations

    the shepherd fold

    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
    clas
    -0.07
     Kam
    -0.07
     rand
    -0.07
    ables
    -0.07
     Blanch
    -0.07
    Credits
    -0.07
     Ones
    -0.07
     onboard
    -0.07
     Richards
    -0.06
    rand
    -0.06
    POSITIVE LOGITS
    aire
    0.12
    jah
    0.11
    erval
    0.11
    atis
    0.11
    /is
    0.11
     Ting
    0.11
    pga
    0.11
    avax
    0.11
     Stein
    0.11
     Valle
    0.10
    Activations Density 0.103%

    No Known Activations