© 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. 29178
    Prev
    Next
    INDEX
    Explanations

    Xavier, Xabi, XV

    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
    /export
    -0.14
     exotic
    -0.13
    _excel
    -0.11
     exponent
    -0.11
    _execute
    -0.11
     expend
    -0.10
    _ex
    -0.10
    erson
    -0.10
    otta
    -0.10
     exon
    -0.10
    POSITIVE LOGITS
    EMPLARY
    0.18
    avier
    0.13
    remely
    0.13
    aneous
    0.13
    ander
    0.13
    odus
    0.12
    ordinary
    0.12
    pecially
    0.11
    uat
    0.11
    /import
    0.10
    Activations Density 1.358%

    No Known Activations