© 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. 26522
    Prev
    Next
    INDEX
    Explanations

    larger, bigger, deeper, broader

    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
    inch
    -0.09
    ож
    -0.09
     besides
    -0.09
    arme
    -0.09
     challenger
    -0.09
    elig
    -0.09
    iki
    -0.09
    Bas
    -0.08
    odos
    -0.08
    arf
    -0.08
    POSITIVE LOGITS
     larger
    0.29
     bigger
    0.28
     deeper
    0.23
     broader
    0.22
     Larger
    0.21
     otherwise
    0.21
     fuller
    0.19
     underlying
    0.19
     wider
    0.17
     ultimately
    0.16
    Activations Density 0.631%

    No Known Activations