© 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. 16318
    Prev
    Next
    INDEX
    Explanations

    present invention relates to

    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
    gies
    -0.11
    ster
    -0.10
    ustr
    -0.09
    bing
    -0.09
    fen
    -0.09
    оÑģÑĤÑĮ
    -0.09
    rot
    -0.09
     present
    -0.09
    iness
    -0.09
    ys
    -0.09
    POSITIVE LOGITS
    -day
    0.26
    iments
    0.19
    ational
    0.18
     tense
    0.18
    iment
    0.17
    ations
    0.17
    -Day
    0.15
    ees
    0.15
    azione
    0.13
    ence
    0.13
    Activations Density 0.135%

    No Known Activations