© 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. 6291
    Prev
    Next
    INDEX
    Explanations

    willingfoughtfightvolunteeredstake their livesconflict

    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
    azi
    -0.09
     disp
    -0.09
     Dayton
    -0.08
     Doom
    -0.08
     curiosity
    -0.08
     Florian
    -0.08
     outsider
    -0.08
    elor
    -0.07
     ass
    -0.07
     aston
    -0.07
    POSITIVE LOGITS
     wars
    0.14
     fights
    0.14
     fought
    0.14
     fight
    0.14
     die
    0.12
     fighting
    0.12
     safeguard
    0.12
    fight
    0.12
    Fight
    0.12
     skirm
    0.12
    Activations Density 0.005%

    No Known Activations