© 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. 162362
    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
    asar
    -0.30
    rog
    -0.26
    uru
    -0.25
    =back
    -0.25
    odon
    -0.25
    Sc
    -0.25
    Sy
    -0.25
    çīĽ
    -0.25
    æĬĦ
    -0.25
    anged
    -0.24
    POSITIVE LOGITS
    uktur
    0.27
    害
    0.26
    ä¸įåħį
    0.25
    å¼Ĭ
    0.25
    æĶ¿åºľ
    0.25
    IDTH
    0.24
     mat
    0.24
     patter
    0.24
    åľ°æĸ¹æĶ¿åºľ
    0.24
    æ±īæĹı
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.