© 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. 90075
    Prev
    Next
    INDEX
    Explanations

    cute

    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
    hand
    -0.12
    à¹Į
    -0.11
    hosts
    -0.11
    strand
    -0.11
    otti
    -0.11
    /star
    -0.10
     wiping
    -0.10
    hunter
    -0.10
    led
    -0.10
    hol
    -0.10
    POSITIVE LOGITS
    ening
    0.13
    (er
    0.12
    icle
    0.11
    icles
    0.11
    ernel
    0.09
    est
    0.09
     overload
    0.09
    ened
    0.09
    en
    0.08
    rix
    0.08
    Activations Density 0.005%

    No Known Activations