© 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. 162494
    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
    å¾Īéĩįè¦ģçļĦ
    -0.28
    aval
    -0.27
    VML
    -0.24
     amat
    -0.24
    HEMA
    -0.24
     suicides
    -0.23
    LM
    -0.23
    éĩįçĶŁ
    -0.23
    MLE
    -0.22
    åĪļ好
    -0.22
    POSITIVE LOGITS
    æł·
    0.28
    涨
    0.27
    仪表
    0.26
    ç§ĺ书
    0.25
    iras
    0.25
     اÙĦجÙĨس
    0.25
    nowledge
    0.24
    羣
    0.24
     irr
    0.24
    enia
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.