© 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. 36316
    Prev
    Next
    INDEX
    Explanations

    passenger transportation services

    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
    ä¸įè§ģ
    -0.09
    çIJĨ工大åѦ
    -0.09
    flix
    -0.09
    ìŀ¥
    -0.09
    åŀ£
    -0.09
    ä¾µçķ¥
    -0.09
    _para
    -0.08
    ings
    -0.08
    busters
    -0.08
    umph
    -0.08
    POSITIVE LOGITS
    hip
    0.12
     sạn
    0.10
    -grade
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.08
    erb
    0.08
     Macy
    0.08
    æѤ
    0.08
    èĻIJ
    0.08
    shal
    0.08
    olini
    0.08
    Activations Density 0.007%

    No Known Activations