© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31675
    Prev
    Next
    INDEX
    Explanations

    Japanese and Korean characters

    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
     Ut
    -0.10
    Ĺı
    -0.08
     {?}
    -0.08
     HEL
    -0.08
    ongs
    -0.08
    Ut
    -0.08
    YC
    -0.08
     McCabe
    -0.07
     ?
    -0.07
    ities
    -0.07
    POSITIVE LOGITS
    ãģıãģłãģķãģĦ
    0.13
    ìĦ¸ìļĶ
    0.13
    ëĭ¤
    0.12
    íķ©ëĭĪëĭ¤
    0.11
    ãģ¾ãģĻ
    0.11
    ez
    0.11
    Ĥ¨
    0.11
     please
    0.10
     yourselves
    0.10
    ìĬµëĭĪëĭ¤
    0.10
    Activations Density 0.025%

    No Known Activations