© 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. 16803
    Prev
    Next
    INDEX
    Explanations

    looking for / hiring / want

    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
     nett
    -0.11
    rat
    -0.11
    ï¸
    -0.11
     fle
    -0.10
     McGu
    -0.10
    plural
    -0.10
     lim
    -0.10
    env
    -0.10
    orent
    -0.10
    "),"
    -0.10
    POSITIVE LOGITS
     access
    0.08
     Neg
    0.07
     *__
    0.07
     Cunning
    0.07
     Cutting
    0.07
    culus
    0.07
     Finding
    0.07
    .Strict
    0.07
     Great
    0.07
     straightforward
    0.07
    Activations Density 0.001%

    No Known Activations