© 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. 48424
    Prev
    Next
    INDEX
    Explanations

    rugby league footballer

    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
     tus
    -0.12
     Luca
    -0.12
     padd
    -0.11
     hel
    -0.11
     Parm
    -0.10
     Luigi
    -0.10
     gint
    -0.10
    MinMax
    -0.10
     Lucy
    -0.10
    Pok
    -0.10
    POSITIVE LOGITS
     Raven
    0.30
     Ravens
    0.22
     Titans
    0.21
     Titan
    0.19
     rav
    0.15
    Titan
    0.14
     Robin
    0.14
     Rav
    0.14
    Tit
    0.13
     robin
    0.12
    Activations Density 0.336%

    No Known Activations