© 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. 28493
    Prev
    Next
    INDEX
    Explanations

    positive feedback or commendation

    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
     Ged
    -0.12
     preparations
    -0.11
     unfinished
    -0.11
     precaution
    -0.11
    /calendar
    -0.11
     unlucky
    -0.11
    -equipped
    -0.10
    Playable
    -0.10
    aign
    -0.10
     predictor
    -0.10
    POSITIVE LOGITS
     praise
    0.47
     praising
    0.43
     praises
    0.40
     praised
    0.33
     applause
    0.28
     congrat
    0.27
     accol
    0.26
     admiration
    0.26
     acclaim
    0.25
     applaud
    0.25
    Activations Density 0.120%

    No Known Activations