© 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. 89029
    Prev
    Next
    INDEX
    Explanations

    time units followed by 'to'

    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
     Ged
    -0.10
     seria
    -0.10
    -primary
    -0.10
    OLON
    -0.09
     Ready
    -0.09
     subt
    -0.09
    OutOf
    -0.09
    ICI
    -0.09
     Gul
    -0.09
     Gall
    -0.09
    POSITIVE LOGITS
     available
    0.16
     ample
    0.15
     before
    0.14
     allotted
    0.14
     Available
    0.13
    _available
    0.12
     allowance
    0.12
     remaining
    0.12
     plenty
    0.12
    Available
    0.11
    Activations Density 0.059%

    No Known Activations