© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161647
    Prev
    Next
    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ¨æĪ·æıIJä¾Ľ
    -0.31
    è¦ģæľī
    -0.28
     someday
    -0.28
    客æĪ·æıIJä¾Ľ
    -0.27
     Jerseys
    -0.25
    æĸ¹å¼ıè¿Ľè¡Į
    -0.25
    åľ¨æľªæĿ¥
    -0.24
    ä¸Ģ侧
    -0.24
    æĹ©æĹ¥
    -0.23
    quete
    -0.23
    POSITIVE LOGITS
    ä¸į管
    0.28
     verw
    0.27
    åı¯èĥ½æĢ§
    0.27
    ä¼ļ
    0.26
     heraus
    0.26
    éļıä¹ĭ
    0.25
    ä¹Łä¼ļ
    0.25
    xing
    0.24
    绿èī²
    0.24
    green
    0.23
    Activations Density 0.010%

    No Known Activations