© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39618
    Prev
    Next
    INDEX
    Explanations

    trafficking

    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
    åĻİ
    -0.11
    åĩĨåĪĻ
    -0.10
     Aires
    -0.10
    åħĪè¡Į
    -0.09
    å¤
    -0.09
    åĴĢ
    -0.09
    çķĢ
    -0.09
    _IOS
    -0.08
    亲
    -0.08
    信访
    -0.08
    POSITIVE LOGITS
     trafficking
    0.11
     Traff
    0.11
     traff
    0.10
    奴éļ¶
    0.10
    åĩłå¼ł
    0.09
     Fant
    0.09
    å½¹
    0.09
    èĻIJå¾ħ
    0.09
    åī¥
    0.09
    æݳ
    0.08
    Activations Density 0.118%

    No Known Activations