© 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. 31967
    Prev
    Next
    INDEX
    Explanations

    speaking more or persuading others

    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
    lea
    -0.11
     Daisy
    -0.10
     invit
    -0.10
    ixer
    -0.09
     Armour
    -0.09
     Saud
    -0.09
    ijn
    -0.09
     Crew
    -0.09
     rendez
    -0.09
     cruelty
    -0.09
    POSITIVE LOGITS
     dominating
    0.20
     dominate
    0.18
     dominates
    0.17
     silence
    0.17
     silent
    0.17
     dominated
    0.17
     predomin
    0.17
     dominance
    0.16
     Domin
    0.16
     domination
    0.15
    Activations Density 0.067%

    No Known Activations