© 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. 113393
    Prev
    Next
    INDEX
    Explanations

    list of dates

    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
    QRS
    -0.11
    frei
    -0.10
     Shed
    -0.10
     robes
    -0.10
     Otto
    -0.10
     quil
    -0.10
     microscopic
    -0.10
    ensing
    -0.10
     Abel
    -0.10
     dilig
    -0.10
    POSITIVE LOGITS
    uma
    0.10
     bic
    0.08
     Drew
    0.08
     Lew
    0.08
     persona
    0.08
     sucking
    0.08
     hometown
    0.07
    bum
    0.07
    aven
    0.07
    9
    0.07
    Activations Density 0.001%

    No Known Activations