© 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. 115807
    Prev
    Next
    INDEX
    Explanations

    Setting, Using, Doing, Assembly, Connecting, Adding

    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
    ability
    -0.11
     Merlin
    -0.09
    irs
    -0.09
     XS
    -0.08
    ir
    -0.08
     Kathy
    -0.08
    ubes
    -0.08
     Iso
    -0.08
    ancy
    -0.08
    pur
    -0.08
    POSITIVE LOGITS
     Swing
    0.11
    swing
    0.10
    semble
    0.10
    hiba
    0.09
    aut
    0.09
     swing
    0.09
    849
    0.09
    erk
    0.09
    ahoma
    0.09
    /es
    0.09
    Activations Density 0.054%

    No Known Activations