© 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. 17351
    Prev
    Next
    INDEX
    Explanations

    introducing new things

    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
     Bast
    -0.11
    iges
    -0.10
    ennie
    -0.09
    elow
    -0.09
    oen
    -0.08
    abort
    -0.08
    æį
    -0.08
    oire
    -0.08
    ieber
    -0.08
    IFn
    -0.08
    POSITIVE LOGITS
     introducing
    0.39
     introduce
    0.35
     introduces
    0.32
    roducing
    0.29
     introdu
    0.29
     introduced
    0.26
     introduction
    0.25
     Int
    0.25
     presenting
    0.25
    Int
    0.24
    Activations Density 0.270%

    No Known Activations