© 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. 17337
    Prev
    Next
    INDEX
    Explanations

    single followed by noun

    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
    enz
    -0.09
    aceous
    -0.08
    oric
    -0.08
    sar
    -0.08
    acular
    -0.08
    ulas
    -0.07
    amo
    -0.07
     Irma
    -0.07
    ve
    -0.07
    en
    -0.07
    POSITIVE LOGITS
    tons
    0.21
    /single
    0.20
    -minded
    0.20
    -handed
    0.18
     minded
    0.18
    (single
    0.18
     sided
    0.17
    -single
    0.17
    TON
    0.16
     handed
    0.15
    Activations Density 0.071%

    No Known Activations