© 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. 5324
    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
    ourke
    -0.26
    lug
    -0.25
    RequiredMixin
    -0.25
    ya
    -0.24
    ä¹ĭä¸ĭ
    -0.24
    ÎIJ
    -0.23
    æĭĸ
    -0.23
    æ´»å¾Ĺ
    -0.23
     LICENSE
    -0.23
    odia
    -0.23
    POSITIVE LOGITS
    常å§Ķ
    0.27
    sez
    0.26
    vd
    0.26
    é£İæ³¢
    0.25
    çģ¶
    0.24
     rowspan
    0.24
     hers
    0.24
     Fo
    0.24
    Pe
    0.23
    using
    0.23
    Activations Density 0.118%

    No Known Activations

    This feature has no known activations.