© 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. 88782
    Prev
    Next
    INDEX
    Explanations

    technical identifiers and code

    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
    illy
    -0.07
    <|fim_suffix|>
    -0.07
    lena
    -0.06
    /{{
    -0.06
    orda
    -0.06
     Sp
    -0.06
    inke
    -0.06
     Norris
    -0.06
    lyn
    -0.06
    feld
    -0.06
    POSITIVE LOGITS
     Tradable
    0.12
    /if
    0.12
    -bs
    0.12
     __________________________________
    0.11
     breat
    0.11
     sesame
    0.11
    ....↵↵
    0.11
    /interfaces
    0.11
    âĢ¦↵↵↵↵
    0.11
     Sanford
    0.11
    Activations Density 1.602%

    No Known Activations