© 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. 163128
    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
    iej
    -0.28
    éĿĽ
    -0.28
    .mj
    -0.28
     unavoidable
    -0.26
     (;;)
    -0.24
    chap
    -0.24
    üler
    -0.24
     inorder
    -0.24
    .tpl
    -0.23
     overnight
    -0.23
    POSITIVE LOGITS
    idas
    0.29
    iti
    0.27
    åĪ°æĿ¥
    0.27
    ä¼ģä¸ļæıIJä¾Ľ
    0.25
    驱
    0.25
    èµĭ
    0.25
    esity
    0.25
    è¿IJ
    0.24
    _DRIVE
    0.24
    ä¹ĭéĹ´çļĦ
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.