© 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. 116809
    Prev
    Next
    INDEX
    Explanations

    adverbs describing how actions are performed

    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
     Polit
    -0.11
     Stamp
    -0.11
    olia
    -0.10
    Stamp
    -0.10
    nya
    -0.10
    ond
    -0.10
     pap
    -0.10
     Flour
    -0.10
    hy
    -0.09
    annya
    -0.09
    POSITIVE LOGITS
    /by
    0.10
     Peterson
    0.08
     enough
    0.08
    Uvs
    0.07
     fuss
    0.07
    /as
    0.07
    gens
    0.07
     Clay
    0.07
    bas
    0.07
     Prot
    0.07
    Activations Density 0.162%

    No Known Activations