© 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. 88975
    Prev
    Next
    INDEX
    Explanations

    javascript disabled or not supported

    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
     Cand
    -0.10
    vet
    -0.10
    pla
    -0.10
    lover
    -0.10
     mes
    -0.10
    ukan
    -0.10
     tempered
    -0.09
     jamais
    -0.09
    ụ
    -0.09
    iw
    -0.09
    POSITIVE LOGITS
     obsc
    0.11
     ECM
    0.11
     scripting
    0.11
     Ec
    0.10
     degrade
    0.09
     degradation
    0.09
     emulation
    0.09
     ecological
    0.09
     detected
    0.08
    DisplayStyle
    0.08
    Activations Density 0.130%

    No Known Activations