© 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. 47435
    Prev
    Next
    INDEX
    Explanations

    det, Det, detest, detrus, detour, detrend, detached, detekt

    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
    aison
    -0.08
     Maid
    -0.07
     qu
    -0.07
    itations
    -0.07
     baff
    -0.07
    acula
    -0.07
     Osborne
    -0.07
    igos
    -0.07
     streak
    -0.07
    organ
    -0.07
    POSITIVE LOGITS
     det
    0.13
     Det
    0.12
    nw
    0.11
    cq
    0.11
     unas
    0.11
     dét
    0.11
    /GL
    0.11
    yro
    0.11
     divorced
    0.11
    tol
    0.11
    Activations Density 0.003%

    No Known Activations