© 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. 4971
    Prev
    Next
    INDEX
    Explanations

    invite comments or feedback

    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
     trans
    -0.07
     gr
    -0.07
     abandonment
    -0.07
    iera
    -0.07
    688
    -0.07
     hier
    -0.06
     divert
    -0.06
     set
    -0.06
     bord
    -0.06
     culp
    -0.06
    POSITIVE LOGITS
     commenting
    0.17
     feedback
    0.16
     comment
    0.16
     Feedback
    0.15
    feedback
    0.15
     Comment
    0.15
     criticisms
    0.15
     critic
    0.15
     criticism
    0.15
     COMMENTS
    0.15
    Activations Density 0.039%

    No Known Activations