© 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. 163295
    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
    ç»į
    -0.28
     alike
    -0.28
    åĨĪ
    -0.27
    éĺŁä¼į
    -0.26
    æ½
    -0.25
    èĭ¦
    -0.24
    оÑı
    -0.24
    æ¾ľ
    -0.24
    ä¸Ģ身
    -0.23
     Guard
    -0.23
    POSITIVE LOGITS
    istar
    0.29
    orough
    0.27
    obuf
    0.27
    EntityManager
    0.25
    tram
    0.25
    remen
    0.25
    ãģ¤ãģı
    0.25
    tru
    0.24
    ưỡng
    0.24
    .osgi
    0.24
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.