© 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. 90810
    Prev
    Next
    INDEX
    Explanations

    stay updated or connected

    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
     Mish
    -0.09
     emot
    -0.09
    ernet
    -0.08
    cept
    -0.08
    mir
    -0.08
     unre
    -0.08
     selectively
    -0.08
     scre
    -0.08
    /id
    -0.08
    steller
    -0.08
    POSITIVE LOGITS
     updated
    0.14
     informed
    0.13
     stay
    0.13
     abre
    0.13
     stays
    0.12
    æĽ´æĸ°
    0.12
     plugged
    0.11
    UpdateTime
    0.11
     updates
    0.11
    updated
    0.11
    Activations Density 0.013%

    No Known Activations