© 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. 11943
    Prev
    Next
    INDEX
    Explanations

    purpose, reason, needs

    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
     Bod
    -0.10
    æĽ¿
    -0.08
     Welfare
    -0.08
     Waist
    -0.08
    èĩªçĦ¶
    -0.07
    olib
    -0.07
    ä¸ĭæĿ¥çļĦ
    -0.07
    ä»ĭ
    -0.07
    _TIM
    -0.07
    é¢ı
    -0.07
    POSITIVE LOGITS
     purposes
    0.26
    缮çļĦ
    0.22
    çļĦ缮çļĦ
    0.21
    çĶ¨éĢĶ
    0.18
     purpose
    0.18
    ä¸ºçĽ®çļĦ
    0.16
    Purpose
    0.15
     목ìłģ
    0.15
    purpose
    0.14
     PURPOSE
    0.14
    Activations Density 0.076%

    No Known Activations