© 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. 17577
    Prev
    Next
    INDEX
    Explanations

    hook-related terms

    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
     Crown
    -0.08
     figured
    -0.08
     jp
    -0.07
     Clarkson
    -0.07
    SED
    -0.07
    puter
    -0.07
     Daisy
    -0.07
    zier
    -0.07
    canf
    -0.07
    mut
    -0.07
    POSITIVE LOGITS
    strap
    0.13
    eries
    0.12
    stra
    0.12
    ugg
    0.11
    ipi
    0.11
    HLT
    0.11
    edly
    0.10
    enga
    0.10
    emons
    0.10
     lash
    0.10
    Activations Density 0.002%

    No Known Activations