© 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. 7324
    Prev
    Next
    INDEX
    Explanations

    friend or foe names

    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
     legit
    -0.10
     vanity
    -0.09
     congest
    -0.09
    utes
    -0.09
    nv
    -0.08
     moot
    -0.08
    /interfaces
    -0.08
    fte
    -0.08
     seedu
    -0.08
     mgr
    -0.08
    POSITIVE LOGITS
     Friend
    0.09
     bef
    0.09
    RIEND
    0.09
    Friendly
    0.09
    Friend
    0.08
     Cli
    0.08
     foe
    0.08
     Como
    0.08
     Friendship
    0.08
     Chill
    0.08
    Activations Density 0.241%

    No Known Activations