© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16687
    Prev
    Next
    INDEX
    Explanations

    depending on

    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
    asse
    -0.08
     jag
    -0.08
    otic
    -0.08
     Kaplan
    -0.08
    pun
    -0.08
     Alger
    -0.08
    .fn
    -0.08
    elay
    -0.08
    fn
    -0.08
    alia
    -0.08
    POSITIVE LOGITS
     if
    0.19
     depending
    0.19
     females
    0.18
     younger
    0.18
     males
    0.18
    depending
    0.17
     Depending
    0.17
     For
    0.17
    For
    0.17
    Depending
    0.17
    Activations Density 1.895%

    No Known Activations