© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92482
    Prev
    Next
    INDEX
    Explanations

    negative immoral actions

    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
    Negative Logits
     cautiously
    -0.09
    -less
    -0.09
     ðŁĺī
    -0.09
    —but
    -0.09
     ðŁĺĢ
    -0.09
     ;)
    -0.08
    ault
    -0.08
     (?)
    -0.08
     ðŁĻĤ
    -0.08
    lessness
    -0.08
    POSITIVE LOGITS
     disguised
    0.27
     mas
    0.24
    mas
    0.17
     Mas
    0.16
     MAS
    0.16
     disgu
    0.15
    Mas
    0.15
     masked
    0.15
     pretending
    0.15
     disguise
    0.15
    Activations Density 0.265%

    No Known Activations