© 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. 31845
    Prev
    Next
    INDEX
    Explanations

    hours, dollars, percent, pounds

    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
    olah
    -0.09
    uppy
    -0.07
    å¼Ĥ
    -0.07
     fray
    -0.07
     dressing
    -0.07
    akin
    -0.07
    wine
    -0.07
     ne
    -0.07
     improvis
    -0.07
     firstly
    -0.07
    POSITIVE LOGITS
     years
    0.23
     minutes
    0.21
     dollars
    0.20
     pounds
    0.19
     ounces
    0.19
    years
    0.18
     months
    0.18
     percent
    0.18
     hours
    0.18
     inches
    0.18
    Activations Density 0.153%

    No Known Activations