© 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. 112821
    Prev
    Next
    INDEX
    Explanations

    consist of

    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
    arna
    -0.10
    quila
    -0.09
    pha
    -0.09
    lek
    -0.09
    Tick
    -0.08
    ielding
    -0.08
     phys
    -0.08
    places
    -0.08
    onde
    -0.08
    s
    -0.08
    POSITIVE LOGITS
    ently
    0.17
    encies
    0.17
    antly
    0.15
    istent
    0.15
    antine
    0.13
    ensus
    0.13
    istency
    0.13
    enza
    0.11
    ence
    0.11
    idine
    0.10
    Activations Density 0.055%

    No Known Activations