© 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. 90101
    Prev
    Next
    INDEX
    Explanations

    grid related syntax

    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
    hood
    -0.11
    SCO
    -0.11
     bush
    -0.10
    odia
    -0.09
     Ping
    -0.09
    vester
    -0.08
    oring
    -0.08
    asz
    -0.08
    ussen
    -0.08
    mil
    -0.08
    POSITIVE LOGITS
    iron
    0.19
    lock
    0.16
    BagConstraints
    0.15
    locked
    0.15
    .Grid
    0.14
    /Grid
    0.14
    /grid
    0.13
    (grid
    0.13
    (Grid
    0.13
     grid
    0.12
    Activations Density 0.046%

    No Known Activations