© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10212
    Prev
    Next
    INDEX
    Explanations

    banning or forbidden things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    çŀİ
    -0.09
    ç¢Į
    -0.09
     bá»ģ
    -0.09
    è¿Ĥ
    -0.09
    å°ı康
    -0.09
     Seam
    -0.09
    é¥ķ
    -0.08
    åįļæĸĩ
    -0.08
     Moody
    -0.08
    _Selection
    -0.08
    POSITIVE LOGITS
    ç¦ģ
    0.21
    ç¦ģæŃ¢
    0.20
     banned
    0.18
     bans
    0.15
    ç¦ģå¿Į
    0.14
    严ç¦ģ
    0.14
     ban
    0.13
     banning
    0.13
     outlaw
    0.13
     forbidden
    0.13
    Activations Density 0.247%

    No Known Activations