© 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. 4831
    Prev
    Next
    INDEX
    Explanations

    share, like, link, and comment

    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
    summ
    -0.10
     charset
    -0.09
    dana
    -0.08
    antry
    -0.08
     spans
    -0.08
     OR
    -0.08
    lah
    -0.08
     prov
    -0.08
    rganization
    -0.08
     forc
    -0.08
    POSITIVE LOGITS
    utral
    0.09
    ollar
    0.09
    utr
    0.08
     outright
    0.08
    ìŀĦ
    0.08
     metro
    0.08
     Werner
    0.08
    ikes
    0.08
    ét
    0.08
     Cly
    0.08
    Activations Density 0.294%

    No Known Activations