© 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. 90170
    Prev
    Next
    INDEX
    Explanations

    D names and words

    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
    }\.[
    -0.11
    kad
    -0.08
     lace
    -0.08
    owi
    -0.08
     embrace
    -0.08
     brav
    -0.08
    mia
    -0.07
    etta
    -0.07
    wij
    -0.07
     Biz
    -0.07
    POSITIVE LOGITS
    (D
    0.17
    @d
    0.15
    /dr
    0.15
    /D
    0.14
    /d
    0.13
    =D
    0.12
    DOMContentLoaded
    0.11
    "D
    0.11
    (Device
    0.11
    (Database
    0.10
    Activations Density 2.652%

    No Known Activations