© 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. 113385
    Prev
    Next
    INDEX
    Explanations

    30

    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
    sla
    -0.12
    acf
    -0.11
    zeit
    -0.11
    hear
    -0.10
    bies
    -0.10
     Lub
    -0.10
    faith
    -0.10
    hazi
    -0.10
     love
    -0.10
    âĻ¥
    -0.10
    POSITIVE LOGITS
     Jog
    0.08
    ADOS
    0.07
     inaug
    0.07
    èĩ
    0.07
    !!)↵
    0.07
    OTT
    0.07
    cox
    0.07
     indispens
    0.07
    cott
    0.07
     resil
    0.07
    Activations Density 0.004%

    No Known Activations