© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113485
    Prev
    Next
    INDEX
    Explanations

    negative descriptors and insults

    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
    olas
    -0.11
     corpse
    -0.10
    ceans
    -0.10
    amen
    -0.10
     Bronze
    -0.10
     hugs
    -0.10
     hug
    -0.10
     corpses
    -0.10
     Mend
    -0.09
    labs
    -0.09
    POSITIVE LOGITS
     stupid
    0.17
     dumb
    0.15
     mistake
    0.15
    ass
    0.15
     mistakes
    0.14
     idiot
    0.14
     naive
    0.14
     silly
    0.13
     ass
    0.12
     kid
    0.12
    Activations Density 0.005%

    No Known Activations