© 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. 27037
    Prev
    Next
    INDEX
    Explanations

    evil grin; emission; quality of; 18

    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
     pus
    -0.11
     legs
    -0.10
     Arms
    -0.09
    armac
    -0.09
     arms
    -0.09
    legs
    -0.08
     backs
    -0.08
    sb
    -0.08
    rette
    -0.08
     eyeb
    -0.08
    POSITIVE LOGITS
     mischief
    0.12
     victorious
    0.12
     trium
    0.12
     cunning
    0.11
     fox
    0.11
     retarded
    0.11
     Lucifer
    0.11
    FOX
    0.11
     conquer
    0.11
    -know
    0.11
    Activations Density 0.005%

    No Known Activations