© 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. 4967
    Prev
    Next
    INDEX
    Explanations

    code comments and delimiters

    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
    ione
    -0.10
    ivi
    -0.10
    ioni
    -0.08
    lush
    -0.08
    ungi
    -0.08
    Qui
    -0.08
     ,,
    -0.08
     Cad
    -0.08
    chein
    -0.08
    Cad
    -0.07
    POSITIVE LOGITS
    lah
    0.10
     Herz
    0.10
     Wales
    0.09
    utura
    0.09
    vos
    0.09
    errer
    0.09
     Excellent
    0.09
    608
    0.09
    .dk
    0.09
     Rif
    0.09
    Activations Density 0.002%

    No Known Activations