© 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. 7227
    Prev
    Next
    INDEX
    Explanations

    Tom, Tom--, Tom---

    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
     TZ
    -0.10
     unt
    -0.09
    .moves
    -0.09
    flash
    -0.09
    .tt
    -0.09
     Slut
    -0.09
    .manual
    -0.09
     Patty
    -0.09
     Prem
    -0.09
    lte
    -0.09
    POSITIVE LOGITS
    ouce
    0.10
    asz
    0.09
     tom
    0.08
    /sn
    0.08
    czy
    0.08
    ksam
    0.08
    Aqu
    0.08
     purported
    0.08
     plated
    0.08
     ald
    0.08
    Activations Density 0.086%

    No Known Activations