© 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. 32795
    Prev
    Next
    INDEX
    Explanations

    j followed by "izz", "ord", "av", "os", "a"

    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
    /mod
    -0.10
     Emp
    -0.09
     Tinder
    -0.09
     Cabinet
    -0.09
    -mouth
    -0.09
     Meer
    -0.09
    mouth
    -0.09
     feminist
    -0.08
    sexual
    -0.08
     Yelp
    -0.08
    POSITIVE LOGITS
     governors
    0.11
    pong
    0.10
    oi
    0.10
     stiff
    0.10
     subject
    0.09
     SUBJECT
    0.09
    nb
    0.09
    lix
    0.09
    oval
    0.09
     Cli
    0.09
    Activations Density 0.002%

    No Known Activations