© 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. 88560
    Prev
    Next
    INDEX
    Explanations

    overlord

    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
     Peak
    -0.10
     clutch
    -0.10
     egreg
    -0.10
     bloom
    -0.09
     paranormal
    -0.09
     peak
    -0.09
     supernatural
    -0.09
     Locker
    -0.09
     smugg
    -0.09
    /moment
    -0.09
    POSITIVE LOGITS
     slime
    0.10
     Cheat
    0.10
    .jp
    0.10
    éĢĢ
    0.10
     summoned
    0.10
    Translator
    0.10
    abo
    0.09
    Keith
    0.09
     conjug
    0.09
     Freed
    0.09
    Activations Density 0.008%

    No Known Activations