© 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. 4234
    Prev
    Next
    INDEX
    Explanations

    choice; outfits; next; only; best

    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
     completeness
    -0.10
    ÙĦا
    -0.09
    ihn
    -0.09
    elin
    -0.09
    TRA
    -0.09
    vell
    -0.08
    Lint
    -0.08
    frei
    -0.08
     nud
    -0.08
     essentially
    -0.08
    POSITIVE LOGITS
     sooner
    0.25
     stakes
    0.15
     clock
    0.15
     only
    0.15
     journey
    0.15
     ONLY
    0.14
     odds
    0.13
    jour
    0.13
     sky
    0.13
     possibilities
    0.13
    Activations Density 0.144%

    No Known Activations