© 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. 17787
    Prev
    Next
    INDEX
    Explanations

    which is / which accompanies

    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
     suit
    -0.10
     which
    -0.10
     dri
    -0.09
     conveniently
    -0.08
     ve
    -0.08
    -Th
    -0.08
    gil
    -0.08
    ges
    -0.08
     loyal
    -0.08
    048
    -0.07
    POSITIVE LOGITS
     nevertheless
    0.12
     moreover
    0.12
     however
    0.12
    however
    0.11
     nonetheless
    0.11
    tty
    0.11
    means
    0.10
    atz
    0.10
     means
    0.10
    scp
    0.10
    Activations Density 0.222%

    No Known Activations