© 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. 16834
    Prev
    Next
    INDEX
    Explanations

    offend or insult

    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
     vp
    -0.11
     approvals
    -0.11
     undermin
    -0.11
     symmetric
    -0.10
     rim
    -0.10
    513
    -0.10
     warmed
    -0.10
    ืà¸Ń
    -0.10
     approval
    -0.10
     reins
    -0.10
    POSITIVE LOGITS
     dignity
    0.14
     sens
    0.13
     offend
    0.12
     offended
    0.11
     etiquette
    0.11
     deeply
    0.10
     delicate
    0.10
     inadvertently
    0.09
     vested
    0.09
    /off
    0.09
    Activations Density 0.040%

    No Known Activations