© 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. 6318
    Prev
    Next
    INDEX
    Explanations

    Mond, Mund, Eld names and places

    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
    er
    -0.19
    erin
    -0.11
    lights
    -0.08
    erde
    -0.08
    brid
    -0.08
    ding
    -0.08
    cks
    -0.08
    gers
    -0.08
    ators
    -0.08
    bs
    -0.08
    POSITIVE LOGITS
    inho
    0.13
    ed
    0.12
    orf
    0.12
    à¹Į
    0.12
    yne
    0.12
    edb
    0.11
    yh
    0.11
    ahl
    0.11
    itm
    0.11
    erness
    0.11
    Activations Density 0.084%

    No Known Activations