© 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. 49369
    Prev
    Next
    INDEX
    Explanations

    sudden physical reaction

    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
     depress
    -0.11
     shitty
    -0.10
     piss
    -0.10
     briefly
    -0.10
    buff
    -0.09
     depressed
    -0.08
     Shine
    -0.08
    esse
    -0.08
    assen
    -0.08
     suck
    -0.08
    POSITIVE LOGITS
     uncont
    0.15
     ðŁĴ
    0.12
     ðŁĺī
    0.11
     unforgettable
    0.11
     provoked
    0.11
     tempted
    0.10
     irresistible
    0.10
     guaranteed
    0.10
     rewind
    0.10
     involuntary
    0.10
    Activations Density 0.034%

    No Known Activations