© 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. 28829
    Prev
    Next
    INDEX
    Explanations

    sounds like explosion or stopping

    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
    rine
    -0.11
     prov
    -0.10
     Nigel
    -0.09
     flashing
    -0.09
     blinking
    -0.09
     commenting
    -0.09
     actually
    -0.09
     intuitive
    -0.09
     Andrews
    -0.09
    oram
    -0.09
    POSITIVE LOGITS
     overhead
    0.11
    Ended
    0.10
     open
    0.09
     softly
    0.09
     slowly
    0.09
     destruct
    0.09
     shut
    0.09
     downward
    0.09
    sono
    0.08
     twice
    0.08
    Activations Density 0.013%

    No Known Activations