© 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. 113889
    Prev
    Next
    INDEX
    Explanations

    shake

    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
     mentally
    -0.10
     drifting
    -0.10
     drifted
    -0.09
     Sim
    -0.09
     pushing
    -0.09
    adas
    -0.09
    edd
    -0.09
     touching
    -0.09
    ment
    -0.09
     Rounds
    -0.09
    POSITIVE LOGITS
    gle
    0.12
     Demp
    0.11
     hips
    0.10
     uncont
    0.10
     Bunny
    0.10
     techno
    0.10
     bottoms
    0.09
     shakes
    0.09
    kus
    0.09
     shake
    0.09
    Activations Density 0.006%

    No Known Activations