© 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. 47795
    Prev
    Next
    INDEX
    Explanations

    increasingly important or popular

    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
     repeatedly
    -0.12
    zee
    -0.10
     exagger
    -0.10
     transit
    -0.09
     intermitt
    -0.09
     suddenly
    -0.09
     wig
    -0.09
     Brass
    -0.09
     consistently
    -0.09
     underst
    -0.09
    POSITIVE LOGITS
    ope
    0.11
    ive
    0.10
    è¶
    0.10
     cul
    0.09
     sophistication
    0.09
    -es
    0.09
    nv
    0.09
    mnt
    0.09
     Soph
    0.09
    -II
    0.09
    Activations Density 0.380%

    No Known Activations