© 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. 15819
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
     spat
    -0.09
    èª
    -0.09
     tid
    -0.09
    .lift
    -0.08
    erties
    -0.08
    mps
    -0.08
     spraw
    -0.08
    emark
    -0.08
    ispens
    -0.08
     affiliate
    -0.08
    POSITIVE LOGITS
    urer
    0.08
    lund
    0.08
    unas
    0.08
     constit
    0.08
     constitution
    0.08
    ACHER
    0.08
    lbl
    0.07
     Miche
    0.07
     sto
    0.07
     standardized
    0.07
    Activations Density 0.346%

    No Known Activations