© 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. 112793
    Prev
    Next
    INDEX
    Explanations

    riding and equestrian concepts

    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
     blackout
    -0.11
     Kiss
    -0.11
     kiss
    -0.10
     Cres
    -0.10
     Pang
    -0.10
     blind
    -0.09
     Blind
    -0.09
    blind
    -0.09
     tightly
    -0.09
     Wend
    -0.09
    POSITIVE LOGITS
     saddle
    0.20
     rider
    0.18
     riders
    0.17
     riding
    0.17
     empowered
    0.17
     sadd
    0.16
     empowerment
    0.15
     empowering
    0.15
     Riding
    0.15
     ridden
    0.15
    Activations Density 0.013%

    No Known Activations