© 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. 5787
    Prev
    Next
    INDEX
    Explanations

    gym, shower, bath, locker room

    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
     mov
    -0.11
     Cop
    -0.10
     move
    -0.09
     Pawn
    -0.09
    auss
    -0.09
     imm
    -0.08
     Move
    -0.08
     Burg
    -0.08
     beg
    -0.08
    -move
    -0.08
    POSITIVE LOGITS
     shower
    0.34
     showers
    0.32
     locker
    0.29
     Shower
    0.28
    locker
    0.22
     towel
    0.22
     gym
    0.22
     bathing
    0.21
     Locker
    0.20
     bath
    0.19
    Activations Density 0.105%

    No Known Activations