© 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. 47025
    Prev
    Next
    INDEX
    Explanations

    never, not edit, suspicious activity, Russians

    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
     Luz
    -0.10
     bell
    -0.09
     Pow
    -0.09
     labyrinth
    -0.09
     cuckold
    -0.09
     simul
    -0.09
     conscient
    -0.09
     harmless
    -0.09
    aler
    -0.08
    CLE
    -0.08
    POSITIVE LOGITS
     escal
    0.10
    vers
    0.10
     perfection
    0.10
    .Never
    0.10
     Rush
    0.09
     promising
    0.09
     coerc
    0.09
     Immediately
    0.09
     Punch
    0.09
    ulin
    0.08
    Activations Density 0.014%

    No Known Activations