© 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. 4544
    Prev
    Next
    INDEX
    Explanations

    "to" followed by actions or questions

    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
    wich
    -0.10
     yol
    -0.10
    UDA
    -0.09
    oby
    -0.09
     Stamina
    -0.09
     temper
    -0.09
    ermann
    -0.09
    uta
    -0.09
    vik
    -0.09
    nero
    -0.09
    POSITIVE LOGITS
     Campo
    0.10
     mention
    0.10
     Shel
    0.10
    -outline
    0.09
     Rag
    0.09
     Regel
    0.08
    WO
    0.08
    -util
    0.08
     disc
    0.08
     Seiten
    0.08
    Activations Density 0.018%

    No Known Activations