© 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. 113099
    Prev
    Next
    INDEX
    Explanations

    partial word endings

    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
     inference
    -0.10
     infer
    -0.09
    izations
    -0.09
     inse
    -0.08
    illet
    -0.08
     inset
    -0.08
     manners
    -0.08
     intrinsic
    -0.08
    ën
    -0.08
     invention
    -0.08
    POSITIVE LOGITS
    /out
    0.16
    ernational
    0.13
    parable
    0.13
    pection
    0.12
    -Out
    0.12
    ,out
    0.12
    zej
    0.12
     Sabha
    0.11
    rement
    0.11
    edia
    0.11
    Activations Density 0.463%

    No Known Activations