© 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. 31730
    Prev
    Next
    INDEX
    Explanations

    deep + noun

    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
     AC
    -0.09
     Hancock
    -0.08
    ALLY
    -0.08
     sham
    -0.08
    ISTIC
    -0.08
    Triple
    -0.08
    bcc
    -0.08
    ften
    -0.08
    iated
    -0.08
     cheek
    -0.08
    POSITIVE LOGITS
     deep
    0.17
    deep
    0.16
     deeper
    0.15
     Deep
    0.15
    Deep
    0.14
     deepen
    0.12
     down
    0.11
    _deep
    0.11
    .deep
    0.10
     somewhere
    0.10
    Activations Density 0.018%

    No Known Activations