© 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. 26019
    Prev
    Next
    INDEX
    Explanations

    GET HURT

    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
     insults
    -0.10
     boycott
    -0.10
     insult
    -0.09
     condemnation
    -0.09
     punished
    -0.09
     punishment
    -0.09
     offended
    -0.09
    Dismiss
    -0.09
     Ek
    -0.08
    Attack
    -0.08
    POSITIVE LOGITS
     Laf
    0.11
     Tent
    0.11
    smart
    0.11
     twee
    0.10
    dos
    0.10
     gan
    0.10
     tug
    0.10
     Lynn
    0.10
     smart
    0.10
     Roe
    0.10
    Activations Density 0.051%

    No Known Activations