© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113784
    Prev
    Next
    INDEX
    Explanations

    speech related compound words

    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
    arend
    -0.08
    ored
    -0.08
    ous
    -0.08
     Chapman
    -0.07
    aton
    -0.07
    oured
    -0.07
    uar
    -0.07
     est
    -0.07
     stor
    -0.07
     Hardcore
    -0.07
    POSITIVE LOGITS
    lessness
    0.16
    lessly
    0.15
    -Language
    0.15
    yer
    0.15
     imped
    0.15
    writers
    0.15
    -language
    0.15
    writer
    0.14
    less
    0.14
    (es
    0.14
    Activations Density 0.026%

    No Known Activations