© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 91905
    Prev
    Next
    INDEX
    Explanations

    words ending in ly or ley

    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
    adin
    -0.11
     Challenger
    -0.10
    enschaft
    -0.10
    odel
    -0.10
    ipp
    -0.10
    lies
    -0.09
     Fro
    -0.09
    mits
    -0.09
    otron
    -0.09
    avel
    -0.09
    POSITIVE LOGITS
     Acres
    0.08
     ut
    0.08
     propor
    0.08
     relying
    0.08
    doing
    0.08
     Doing
    0.08
    yet
    0.08
     barber
    0.08
     reveal
    0.08
    xt
    0.08
    Activations Density 0.001%

    No Known Activations