© 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. 18295
    Prev
    Next
    INDEX
    Explanations

    mutual benefit win-win

    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
    ><!--
    -0.10
    achel
    -0.09
     ux
    -0.09
     cav
    -0.09
     acronym
    -0.09
    bn
    -0.09
     chatt
    -0.09
    SEQ
    -0.08
    bes
    -0.08
     reveal
    -0.08
    POSITIVE LOGITS
     mutually
    0.54
     mutual
    0.49
     Mutual
    0.39
     symb
    0.36
     everybody
    0.34
     everyone
    0.33
     Everybody
    0.32
    mut
    0.29
     Everyone
    0.29
    Mut
    0.29
    Activations Density 0.235%

    No Known Activations