© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 31661
    Prev
    Next
    INDEX
    Explanations

    surrounded by friends or family

    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
     competitor
    -0.10
     traveler
    -0.10
    Hat
    -0.10
    OLLOW
    -0.10
    SPA
    -0.10
     predecessor
    -0.09
     Yours
    -0.09
     prototype
    -0.09
     suger
    -0.09
    stub
    -0.09
    POSITIVE LOGITS
     friends
    0.58
     Friends
    0.46
    friends
    0.45
    Friends
    0.42
     friendships
    0.36
     family
    0.36
    _friends
    0.35
     FRIEND
    0.33
     relatives
    0.31
    riends
    0.31
    Activations Density 0.412%

    No Known Activations