© 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. 112939
    Prev
    Next
    INDEX
    Explanations

    checking code and files

    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
    reso
    -0.11
    acht
    -0.11
    zy
    -0.10
    ozy
    -0.10
     tra
    -0.10
    ech
    -0.10
     cryst
    -0.10
    Variant
    -0.10
     hx
    -0.10
    ese
    -0.10
    POSITIVE LOGITS
     expecting
    0.16
    —it
    0.13
    âĢ¦it
    0.11
     saw
    0.11
    :
    0.10
    —they
    0.10
     hoping
    0.10
     reveal
    0.09
     discover
    0.09
    -it
    0.09
    Activations Density 0.148%

    No Known Activations