© 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. 47964
    Prev
    Next
    INDEX
    Explanations

    strangers or enemies

    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
     rog
    -0.09
     Tos
    -0.08
     Standing
    -0.08
     Tob
    -0.08
     Maver
    -0.08
    standing
    -0.07
    /int
    -0.07
     Clubs
    -0.07
     Rog
    -0.07
     ToDo
    -0.07
    POSITIVE LOGITS
     strangers
    0.18
     stranger
    0.17
     online
    0.16
    /random
    0.14
     anonymously
    0.12
     Stranger
    0.12
    online
    0.11
     worldwide
    0.11
     randomly
    0.11
    icc
    0.11
    Activations Density 0.007%

    No Known Activations