© 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. 28671
    Prev
    Next
    INDEX
    Explanations

    Class: Name, Color: Description, construction/ischem

    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
     Sant
    -0.08
     Tamb
    -0.08
    ,time
    -0.08
     damn
    -0.08
    /en
    -0.08
    arden
    -0.08
    steps
    -0.07
    abl
    -0.07
     st
    -0.07
     expense
    -0.07
    POSITIVE LOGITS
    esor
    0.11
    avy
    0.11
     beide
    0.10
    visa
    0.10
     Moor
    0.10
    ..<
    0.10
    itur
    0.10
     Smy
    0.10
    843
    0.10
     viên
    0.10
    Activations Density 0.001%

    No Known Activations