© 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. 112313
    Prev
    Next
    INDEX
    Explanations

    heard of

    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
     Elias
    -0.10
    ucci
    -0.09
    odi
    -0.08
     Jensen
    -0.08
    coni
    -0.08
     past
    -0.08
     Dek
    -0.08
    odia
    -0.08
    cken
    -0.07
    amat
    -0.07
    POSITIVE LOGITS
     heard
    0.37
     Heard
    0.35
    heard
    0.31
     unheard
    0.29
     hear
    0.24
     hears
    0.23
    åIJ¬
    0.22
    hear
    0.20
     hearing
    0.20
     Hear
    0.20
    Activations Density 0.112%

    No Known Activations