© 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. 32722
    Prev
    Next
    INDEX
    Explanations

    constructor or time.tm_min

    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
     hypotheses
    -0.26
    #ifndef
    -0.24
     hypothesis
    -0.24
     hoses
    -0.24
     QHBoxLayout
    -0.23
     highways
    -0.23
     histograms
    -0.23
    ,height
    -0.22
     Hawaii
    -0.22
     histogram
    -0.22
    POSITIVE LOGITS
    .ResponseEntity
    0.12
     Vertical
    0.09
     vertically
    0.09
    åĪĨéĴŁ
    0.08
    ency
    0.08
    Minutes
    0.08
     minutes
    0.08
    .Vertical
    0.08
     Sawyer
    0.08
     vertical
    0.08
    Activations Density 2.311%

    No Known Activations