© 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. 19-TRANSCODER-HP
    7. 5779
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çł´
    -0.28
    ioneer
    -0.28
     Whole
    -0.27
     concern
    -0.26
    éĩıåĮĸ
    -0.26
    çľĭæ³ķ
    -0.25
    缺å°ij
    -0.25
    Om
    -0.25
    åıĤåĬł
    -0.25
    缮çĿ¹
    -0.24
    POSITIVE LOGITS
    ä¸įå¾Ĺå·²
    0.25
    èĢħçļĦ
    0.25
    éŃĥ
    0.25
    adge
    0.25
     Requests
    0.25
    acent
    0.24
    ản
    0.24
     `'
    0.24
    æĶ»çķ¥
    0.23
    è¿Ļæīįæĺ¯
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.