© 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. 90474
    Prev
    Next
    INDEX
    Explanations

    Mar followed by names

    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
    .ly
    -0.11
     Lucia
    -0.10
    occo
    -0.10
     Tears
    -0.10
    _prog
    -0.09
     GFX
    -0.09
     Haut
    -0.09
     clash
    -0.09
    ihad
    -0.09
    opsis
    -0.09
    POSITIVE LOGITS
    mit
    0.11
     Cached
    0.10
    /board
    0.10
    mmo
    0.09
     Admir
    0.09
    ston
    0.09
    well
    0.09
    iele
    0.08
    illion
    0.08
    lar
    0.08
    Activations Density 0.006%

    No Known Activations