© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48435
    Prev
    Next
    INDEX
    Explanations

    verbs of perception and creation

    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
     exactly
    -0.08
    rost
    -0.08
    fx
    -0.08
    ying
    -0.08
     Exactly
    -0.08
     supplemental
    -0.08
     lad
    -0.08
     Xin
    -0.07
    os
    -0.07
    ç¯
    -0.07
    POSITIVE LOGITS
     them
    0.13
     it
    0.11
    them
    0.11
     Bere
    0.10
    ouch
    0.09
     mak
    0.09
    671
    0.09
     yours
    0.09
    аÑģ
    0.09
     Pou
    0.09
    Activations Density 0.059%

    No Known Activations