© 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. 17385
    Prev
    Next
    INDEX
    Explanations

    Lord bless

    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
     repost
    -0.07
     sle
    -0.07
     punct
    -0.07
     VA
    -0.06
     connexion
    -0.06
     scr
    -0.06
     efficiently
    -0.06
     paw
    -0.06
    CON
    -0.06
    acie
    -0.06
    POSITIVE LOGITS
     forbid
    0.21
     bless
    0.17
     save
    0.15
     forgive
    0.15
     Above
    0.15
     above
    0.15
    above
    0.14
     Almighty
    0.14
     HELP
    0.14
     help
    0.14
    Activations Density 0.015%

    No Known Activations