© 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. 91067
    Prev
    Next
    INDEX
    Explanations

    scrap paper and books

    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
    /Base
    -0.08
     barr
    -0.08
    stage
    -0.07
     dizzy
    -0.07
     Fro
    -0.07
    udi
    -0.07
    ########
    -0.07
     NOI
    -0.07
     fried
    -0.07
    &r
    -0.07
    POSITIVE LOGITS
     scrap
    0.21
    heap
    0.19
     Scrap
    0.19
     scraps
    0.19
    yard
    0.17
     heap
    0.17
    booking
    0.16
     Heap
    0.15
    book
    0.14
    books
    0.14
    Activations Density 0.009%

    No Known Activations