© 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. 18565
    Prev
    Next
    INDEX
    Explanations

    forbidden or prohibited

    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
     ext
    -0.09
     sincerely
    -0.07
    izo
    -0.07
     miscellaneous
    -0.07
     deficiencies
    -0.07
     Radi
    -0.07
     fairness
    -0.07
     pimp
    -0.07
    isans
    -0.07
     merits
    -0.07
    POSITIVE LOGITS
     forbidden
    0.28
    Forbidden
    0.22
     taboo
    0.22
     Forbidden
    0.21
     prohibited
    0.18
    bidden
    0.18
     forbid
    0.18
    /tab
    0.18
     prohib
    0.17
     forb
    0.16
    Activations Density 0.016%

    No Known Activations