© 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. 112360
    Prev
    Next
    INDEX
    Explanations

    article

    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
    OME
    -0.10
     Gir
    -0.09
    rait
    -0.09
    /Sh
    -0.09
    tings
    -0.09
    /rest
    -0.09
     ugly
    -0.09
    grade
    -0.09
    ement
    -0.09
    ings
    -0.09
    POSITIVE LOGITS
    /video
    0.16
    /videos
    0.13
    -length
    0.12
    /books
    0.11
    /blog
    0.11
    /book
    0.11
     about
    0.11
    /story
    0.10
     titled
    0.10
    /posts
    0.10
    Activations Density 0.072%

    No Known Activations