© 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. 47734
    Prev
    Next
    INDEX
    Explanations

    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
    wan
    -0.11
     textbook
    -0.10
    /colors
    -0.10
    /storage
    -0.10
    alin
    -0.10
    dek
    -0.10
    overe
    -0.10
     booklet
    -0.10
    sing
    -0.10
    coe
    -0.09
    POSITIVE LOGITS
    shelf
    0.24
    ellers
    0.23
    ç±
    0.20
    eller
    0.20
    worm
    0.19
    keeping
    0.19
    lets
    0.19
    elling
    0.18
    stores
    0.17
    -length
    0.15
    Activations Density 0.094%

    No Known Activations