© 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. 46930
    Prev
    Next
    INDEX
    Explanations

    cast spells or rituals

    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
     regenerated
    -0.10
     jams
    -0.10
     luz
    -0.10
    Returned
    -0.10
    ctl
    -0.10
     arb
    -0.09
     Hanson
    -0.09
     Mode
    -0.09
     tent
    -0.09
     kita
    -0.09
    POSITIVE LOGITS
     spell
    0.14
     cast
    0.14
     applied
    0.14
     spells
    0.13
     runes
    0.12
     casting
    0.12
     rune
    0.11
     enacted
    0.11
    casting
    0.11
     Casting
    0.11
    Activations Density 0.189%

    No Known Activations