© 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. 15071
    Prev
    Next
    INDEX
    Explanations

    how to instruct

    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
    ahr
    -0.09
     achie
    -0.08
     ime
    -0.08
     frontier
    -0.08
    rez
    -0.07
     firstly
    -0.07
     these
    -0.07
     Shades
    -0.07
     âĢ
    -0.07
    ove
    -0.07
    POSITIVE LOGITS
    Convertible
    0.11
    ilden
    0.11
     Absolutely
    0.11
     #$
    0.11
    almost
    0.11
     torpedo
    0.10
    Lazy
    0.10
     Really
    0.10
    Viewport
    0.10
     surviv
    0.10
    Activations Density 0.155%

    No Known Activations