© 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. 32889
    Prev
    Next
    INDEX
    Explanations

    Moser, Moselle, Mosquito, Mosley

    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
    mium
    -0.08
     Wolver
    -0.08
     rash
    -0.08
    è½
    -0.07
     ecl
    -0.07
    .asp
    -0.07
     Bye
    -0.07
     thrust
    -0.07
     Comm
    -0.07
    ruz
    -0.07
    POSITIVE LOGITS
    htag
    0.11
    ambique
    0.11
    y
    0.11
     fundamentally
    0.10
     Muss
    0.10
    leh
    0.10
    ,module
    0.10
    elman
    0.10
     misuse
    0.10
     colon
    0.10
    Activations Density 0.062%

    No Known Activations