© 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. 31120
    Prev
    Next
    INDEX
    Explanations

    strongly/greatly encourage/recommend/appreciate

    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
     squarely
    -0.10
     proportion
    -0.10
     absolutely
    -0.09
     Witness
    -0.09
     fortune
    -0.09
    ĺìĿ´
    -0.09
    traction
    -0.09
     logically
    -0.09
    levator
    -0.09
    981
    -0.09
    POSITIVE LOGITS
     recommend
    0.12
     encourage
    0.11
    arde
    0.11
     suspects
    0.11
     recommends
    0.10
    isto
    0.09
     Corm
    0.09
     Uph
    0.09
    ento
    0.09
    åĥı
    0.09
    Activations Density 0.034%

    No Known Activations