© 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. 25865
    Prev
    Next
    INDEX
    Explanations

    positive qualities and benefits

    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
    sher
    -0.11
     Ged
    -0.09
    رÙĪ
    -0.08
     Worse
    -0.08
    GH
    -0.08
     sher
    -0.08
     Myst
    -0.07
    isu
    -0.07
    avec
    -0.07
     rio
    -0.07
    POSITIVE LOGITS
     important
    0.22
     reassuring
    0.21
     appreciated
    0.19
     benefit
    0.19
     priceless
    0.19
    important
    0.19
     comforting
    0.18
     pleasing
    0.18
     commend
    0.18
     invaluable
    0.17
    Activations Density 0.209%

    No Known Activations