© 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. 3898
    Prev
    Next
    INDEX
    Explanations

    locations followed by actions

    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
     mutually
    -0.12
     Heller
    -0.12
    uliar
    -0.12
     venir
    -0.11
     EVEN
    -0.11
    .isUser
    -0.11
    ocrat
    -0.11
    OnError
    -0.11
    eding
    -0.11
    ording
    -0.11
    POSITIVE LOGITS
     trying
    0.14
     awaiting
    0.13
     watching
    0.13
     working
    0.12
     waiting
    0.12
     enjoying
    0.11
     looking
    0.11
     doing
    0.11
     attempting
    0.11
     studying
    0.11
    Activations Density 0.064%

    No Known Activations