© 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. 49992
    Prev
    Next
    INDEX
    Explanations

    use of

    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
    istics
    -0.09
    iasm
    -0.09
    MES
    -0.08
    ERA
    -0.08
    azine
    -0.08
    rand
    -0.08
    /debug
    -0.08
    itics
    -0.08
    ovation
    -0.08
    azines
    -0.08
    POSITIVE LOGITS
    ful
    0.25
    fulness
    0.19
    full
    0.17
    FUL
    0.17
    fixtures
    0.15
    less
    0.15
    cases
    0.15
    fully
    0.14
    case
    0.13
    lessly
    0.13
    Activations Density 0.123%

    No Known Activations