© 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. 6758
    Prev
    Next
    INDEX
    Explanations

    got home and started

    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
     Turnbull
    -0.10
    avo
    -0.10
     Exit
    -0.10
     rooms
    -0.10
     hallway
    -0.10
     Rooms
    -0.09
     mornings
    -0.09
    /actions
    -0.09
    ustria
    -0.09
     exit
    -0.09
    POSITIVE LOGITS
     shower
    0.21
     showers
    0.18
     Shower
    0.17
     online
    0.15
     workout
    0.14
     yoga
    0.14
     Yoga
    0.14
     cleaned
    0.14
     exercise
    0.13
     exercised
    0.13
    Activations Density 0.044%

    No Known Activations