© 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. 91441
    Prev
    Next
    INDEX
    Explanations

    moi, mo, moët, moths, mother, moose, moxie

    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
    lu
    -0.08
    odate
    -0.08
    shift
    -0.07
     unrelated
    -0.07
    idad
    -0.07
     reb
    -0.07
    ker
    -0.07
    st
    -0.06
    mat
    -0.06
    bu
    -0.06
    POSITIVE LOGITS
    aning
    0.16
    ieties
    0.16
    zzarella
    0.16
    oney
    0.15
     mo
    0.14
    ths
    0.14
    quette
    0.13
    omba
    0.13
    oving
    0.13
    ehler
    0.13
    Activations Density 0.012%

    No Known Activations