© 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. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56826
    Prev
    Next
    INDEX
    Explanations

    companies, finance, economics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ³ķè§Ħ
    -0.29
    好ä¸į好
    -0.27
    jis
    -0.27
    åıijå±ķæĸ¹åIJij
    -0.27
    è¦ģæĬĬ
    -0.26
    èµ°åĩºæĿ¥
    -0.26
     Burgess
    -0.26
    驾驶è¯ģ
    -0.26
     copyrighted
    -0.25
    å·¥ä½ľæķĪçİĩ
    -0.25
    POSITIVE LOGITS
    æĬĺ
    0.28
    éļIJ
    0.26
    aint
    0.26
    éĢīæĭ©
    0.26
     cho
    0.25
    è¡Įéķ¿
    0.24
    й
    0.24
    _mv
    0.24
    容åĻ¨
    0.24
    ayı
    0.24
    Activations Density 0.005%

    No Known Activations