© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 27717
    Prev
    Next
    INDEX
    Explanations

    a filterchain, propertydescriptor, axiom, constructor, violation

    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
     fal
    -0.08
    gov
    -0.08
    â̦and
    -0.08
     whose
    -0.08
     and
    -0.08
     Saunders
    -0.07
    ahas
    -0.07
    resents
    -0.07
     Malone
    -0.07
     Ric
    -0.07
    POSITIVE LOGITS
     scrolled
    0.11
     =↵↵
    0.10
     occurs
    0.10
    .....↵↵
    0.10
     =č↵
    0.10
    ulen
    0.10
    kel
    0.10
     =↵
    0.10
     scrolling
    0.10
    ffa
    0.10
    Activations Density 0.124%

    No Known Activations