© 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. 48291
    Prev
    Next
    INDEX
    Explanations

    ad followed by names

    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
    iya
    -0.16
    i
    -0.15
    ding
    -0.14
    ian
    -0.14
    ata
    -0.13
    r
    -0.12
    y
    -0.12
    os
    -0.12
    as
    -0.12
    iÄĩ
    -0.12
    POSITIVE LOGITS
    nock
    0.10
    urai
    0.10
    \Component
    0.10
    eger
    0.10
    egg
    0.09
    .qq
    0.09
    jective
    0.09
    tea
    0.09
    egan
    0.08
    pad
    0.08
    Activations Density 0.065%

    No Known Activations