© 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. 5434
    Prev
    Next
    INDEX
    Explanations

    various types of items

    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
    rch
    -0.08
    èĢ
    -0.07
     hopeful
    -0.07
     takeover
    -0.07
     ponder
    -0.07
    upy
    -0.07
     rund
    -0.07
     delightful
    -0.07
     Positioned
    -0.07
     momentos
    -0.07
    POSITIVE LOGITS
     Various
    0.12
     vivastreet
    0.11
     specialised
    0.11
     various
    0.10
    /screen
    0.10
    .createFrom
    0.09
    __':↵
    0.09
     sexual
    0.09
    ,alpha
    0.09
     specially
    0.09
    Activations Density 0.040%

    No Known Activations