© 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. 91578
    Prev
    Next
    INDEX
    Explanations

    best friend or employee

    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
    aji
    -0.09
     chim
    -0.08
     Chim
    -0.08
     piles
    -0.08
     unp
    -0.08
    ocos
    -0.08
    alary
    -0.08
     motto
    -0.07
    å½
    -0.07
     mastery
    -0.07
    POSITIVE LOGITS
     friend
    0.18
     Friend
    0.18
    friend
    0.14
     friends
    0.14
    friends
    0.13
     FRIEND
    0.13
    Friend
    0.13
     guess
    0.13
    /w
    0.13
    guess
    0.12
    Activations Density 0.024%

    No Known Activations