© 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. 18252
    Prev
    Next
    INDEX
    Explanations

    documentaries, VICE, names, numbers

    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
     enchanted
    -0.09
     Plum
    -0.09
     
    -0.09
    avana
    -0.09
    utenberg
    -0.09
     Pumpkin
    -0.09
     signatures
    -0.08
    861
    -0.08
    iola
    -0.08
     Suz
    -0.08
    POSITIVE LOGITS
    VICE
    0.20
     VIC
    0.15
     vice
    0.14
     Vice
    0.13
     IRC
    0.11
     documentaries
    0.11
    Correction
    0.11
     heroin
    0.10
     DEA
    0.10
    vice
    0.10
    Activations Density 0.028%

    No Known Activations