© 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. 16583
    Prev
    Next
    INDEX
    Explanations

    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
    WI
    -0.08
     purs
    -0.08
     WI
    -0.08
     renew
    -0.08
     authorized
    -0.08
     Cyrus
    -0.07
     Pascal
    -0.07
    Authorized
    -0.07
     purse
    -0.07
     goodness
    -0.07
    POSITIVE LOGITS
     Feedback
    0.30
     feedback
    0.28
    Feedback
    0.28
    feedback
    0.23
    _feedback
    0.21
    -feedback
    0.21
    .feedback
    0.18
    (feed
    0.16
    .Feed
    0.16
    edback
    0.14
    Activations Density 0.151%

    No Known Activations