© 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. 26229
    Prev
    Next
    INDEX
    Explanations

    new and improved

    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
    rego
    -0.10
    +:
    -0.10
    wap
    -0.10
    ewn
    -0.09
    nze
    -0.09
    ahoma
    -0.09
     knowledgeable
    -0.09
    @dynamic
    -0.09
    akest
    -0.09
     diligence
    -0.09
    POSITIVE LOGITS
     exciting
    0.18
     unfamiliar
    0.16
     unknown
    0.13
     different
    0.13
     unexpected
    0.13
     new
    0.12
     improved
    0.12
     additional
    0.12
     unique
    0.11
     novel
    0.11
    Activations Density 0.071%

    No Known Activations