© 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. 29171
    Prev
    Next
    INDEX
    Explanations

    drawing weapon or sword

    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
     inexperienced
    -0.11
     Rowe
    -0.11
    iali
    -0.10
     decoration
    -0.10
     dressing
    -0.10
     htt
    -0.10
     oral
    -0.10
    /var
    -0.10
     stringify
    -0.10
     pillow
    -0.10
    POSITIVE LOGITS
     unpack
    0.15
     drawn
    0.14
     pulled
    0.14
     drew
    0.13
     unveiled
    0.13
     pocket
    0.13
     Pull
    0.12
     unfolded
    0.12
     extracted
    0.12
     produced
    0.12
    Activations Density 0.096%

    No Known Activations