© 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. 29042
    Prev
    Next
    INDEX
    Explanations

    South Park secondary

    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
     Busty
    -0.11
     Bench
    -0.11
     Merlin
    -0.11
    Bes
    -0.10
     Buffy
    -0.10
     lingerie
    -0.10
     witch
    -0.10
     Kavanaugh
    -0.10
    amil
    -0.10
     foremost
    -0.10
    POSITIVE LOGITS
     Mario
    0.10
     Sonic
    0.10
     Luigi
    0.09
     Yoshi
    0.09
     Bow
    0.09
    -generic
    0.09
     Tele
    0.09
     Sponge
    0.09
     behaviours
    0.09
     GX
    0.09
    Activations Density 0.073%

    No Known Activations