© 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. 112723
    Prev
    Next
    INDEX
    Explanations

    words ending in -old, -ars, -ek, -ape, -ires, -ripe, -od, -rike, alk

    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
    cele
    -0.11
    osed
    -0.11
     pom
    -0.10
    -exp
    -0.10
    UTO
    -0.10
     tert
    -0.10
    ANCH
    -0.10
     Rav
    -0.09
    fav
    -0.09
    -dem
    -0.09
    POSITIVE LOGITS
    yard
    0.10
    heel
    0.08
    lip
    0.08
     overt
    0.08
    lu
    0.08
    et
    0.08
    picker
    0.08
    ream
    0.08
     Muse
    0.08
    PACE
    0.08
    Activations Density 0.378%

    No Known Activations