© 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. 34593
    Prev
    Next
    INDEX
    Explanations

    communication and contact

    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
    aida
    -0.09
    ç³Ĭ
    -0.09
    -commercial
    -0.09
     Cougar
    -0.08
    ä¸ģ
    -0.08
     sore
    -0.08
    è´Ł
    -0.08
    积æŀģéħįåIJĪ
    -0.08
     Nack
    -0.08
    urette
    -0.08
    POSITIVE LOGITS
    èģĶç³»
    0.15
     contact
    0.13
     ÑģвÑıзи
    0.12
    éĢļè¯Ŀ
    0.11
    åij¼
    0.11
    éĢļä¿¡
    0.11
    éĢļ讯
    0.11
    contact
    0.11
     contacto
    0.10
     contacting
    0.10
    Activations Density 0.106%

    No Known Activations