© 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. 28175
    Prev
    Next
    INDEX
    Explanations

    vibrations or 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
    strand
    -0.08
    WND
    -0.08
    oha
    -0.08
    kov
    -0.08
     swing
    -0.08
     clo
    -0.08
     spotlight
    -0.08
    -archive
    -0.08
    inin
    -0.08
    lock
    -0.08
    POSITIVE LOGITS
     vibrations
    0.26
     vibration
    0.25
     Vibr
    0.22
     vibr
    0.20
     vibrating
    0.18
     resonate
    0.18
     resonance
    0.17
     vib
    0.16
     rever
    0.16
     vibes
    0.16
    Activations Density 0.055%

    No Known Activations