© 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. 29849
    Prev
    Next
    INDEX
    Explanations

    states, cases, time, weight, script, system

    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
     \↵
    -0.13
     &↵
    -0.11
     /↵
    -0.10
    IFn
    -0.10
     Vide
    -0.10
     &&č↵
    -0.09
     =č↵
    -0.09
     \č↵
    -0.09
     ||č↵
    -0.09
    lete
    -0.09
    POSITIVE LOGITS
    gether
    0.27
    adays
    0.24
    etheless
    0.19
    odore
    0.17
    ynchronously
    0.17
    wards
    0.17
    bsites
    0.16
    jourd
    0.16
    oretical
    0.16
    theless
    0.16
    Activations Density 0.328%

    No Known Activations