© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33837
    Prev
    Next
    INDEX
    Explanations

    appreciated, much appreciated, encouragement

    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
     prep
    -0.08
     fins
    -0.08
     (?)
    -0.08
    gren
    -0.08
    ungs
    -0.08
     Successfully
    -0.08
     proclaimed
    -0.07
     THEIR
    -0.07
     Hoy
    -0.07
    imo
    -0.07
    POSITIVE LOGITS
     feedback
    0.21
     Feedback
    0.20
    Feedback
    0.18
    feedback
    0.18
    -feedback
    0.17
     constructive
    0.16
    /comments
    0.15
     appreciated
    0.15
     encourage
    0.15
     encouragement
    0.15
    Activations Density 0.012%

    No Known Activations