© 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. 30080
    Prev
    Next
    INDEX
    Explanations

    agreed, finalized, meeting

    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
    olt
    -0.09
     reinterpret
    -0.09
    olen
    -0.09
    ä»Ĭå¹´
    -0.09
     "'
    -0.08
     Cobb
    -0.08
    imers
    -0.08
     mend
    -0.08
    atern
    -0.08
    è¿
    -0.08
    POSITIVE LOGITS
     adj
    0.16
     finalized
    0.15
     agreed
    0.15
     meeting
    0.14
    meeting
    0.13
     recess
    0.13
     optimism
    0.12
     optimistic
    0.12
     agreement
    0.12
     jot
    0.12
    Activations Density 0.155%

    No Known Activations