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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162443
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ç¨ĭ度
    -0.26
    .pitch
    -0.25
    åĴĮä»ĸçļĦ
    -0.25
    è¿ĩ渡
    -0.25
    .flash
    -0.24
     ÑģобÑĢан
    -0.24
    è¨Ģ
    -0.24
     ADDR
    -0.24
    æĶ»çķ¥
    -0.23
    ::__
    -0.23
    POSITIVE LOGITS
    kill
    0.28
     sensitive
    0.27
    ycles
    0.27
    ãĤ¢ãĤ¦ãĥĪ
    0.26
    ieve
    0.25
    eos
    0.25
     sensitivity
    0.25
     patience
    0.25
    ÑģÑĤал
    0.25
    æķıæĦŁ
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.