© 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. 5343
    Prev
    Next
    INDEX
    Explanations

    a [random, character, copy, results, victory]

    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
    aji
    -0.10
     Monument
    -0.09
    cola
    -0.09
     garn
    -0.09
    jie
    -0.09
     ing
    -0.09
    zap
    -0.09
    vez
    -0.09
     lim
    -0.09
    ieve
    -0.09
    POSITIVE LOGITS
    hold
    0.16
     nearby
    0.13
     victory
    0.12
     hold
    0.12
     footh
    0.12
     Nearby
    0.11
     handful
    0.11
     chunks
    0.11
     passage
    0.10
     Mus
    0.10
    Activations Density 0.040%

    No Known Activations