© 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. 49134
    Prev
    Next
    INDEX
    Explanations

    casting ballots or spells

    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
    esi
    -0.10
    ukkan
    -0.10
    ibia
    -0.10
    rena
    -0.09
    -on
    -0.09
    nak
    -0.09
     conduct
    -0.09
     realization
    -0.09
     progress
    -0.08
    ondere
    -0.08
    POSITIVE LOGITS
     spells
    0.17
     aside
    0.17
     spell
    0.17
     Casting
    0.16
     casting
    0.15
     nets
    0.14
     ballot
    0.13
     net
    0.13
     Spell
    0.13
     shadow
    0.13
    Activations Density 0.018%

    No Known Activations