© 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. 4291
    Prev
    Next
    INDEX
    Explanations

    other/first/idea/one followed by being

    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
    odo
    -0.07
    -_
    -0.06
    OLT
    -0.06
    zer
    -0.06
    artz
    -0.06
    olt
    -0.06
     Jerome
    -0.06
     dep
    -0.06
    ope
    -0.06
    607
    -0.06
    POSITIVE LOGITS
     being
    0.63
    being
    0.53
     Being
    0.46
    Being
    0.45
     sendo
    0.34
    -being
    0.34
     siendo
    0.33
    è¢
    0.29
    'être
    0.22
     être
    0.20
    Activations Density 0.366%

    No Known Activations