© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 88375
    Prev
    Next
    INDEX
    Explanations

    powered tools, motors, vibrating

    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
     chem
    -0.10
    isin
    -0.09
     Kok
    -0.09
     carr
    -0.09
     ev
    -0.09
     Ev
    -0.09
     Shan
    -0.09
     ink
    -0.09
     salty
    -0.08
     Morph
    -0.08
    POSITIVE LOGITS
     buzzing
    0.25
     vibrating
    0.22
     motor
    0.21
     vibration
    0.21
     vibrations
    0.20
     vibr
    0.19
     buzz
    0.19
     spinning
    0.19
     motors
    0.18
    motor
    0.18
    Activations Density 0.263%

    No Known Activations