© 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. 112231
    Prev
    Next
    INDEX
    Explanations

    admire or admiration

    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
    ways
    -0.11
    ened
    -0.11
    oria
    -0.11
    iers
    -0.10
    enso
    -0.10
    eya
    -0.10
    è¨Ģ
    -0.10
    ured
    -0.10
    usal
    -0.09
    ought
    -0.09
    POSITIVE LOGITS
    ments
    0.13
    ably
    0.13
     greatly
    0.13
    ingly
    0.11
    mente
    0.10
    alty
    0.10
    -worthy
    0.10
    devil
    0.09
    ously
    0.09
    isable
    0.09
    Activations Density 0.006%

    No Known Activations