© 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. 163523
    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
    rightness
    -0.26
    å®īåħ¨ä¿Ŀéļľ
    -0.26
    eea
    -0.26
    æĬķèµĦåŁºéĩij
    -0.25
    orld
    -0.25
     safest
    -0.24
    quiry
    -0.24
    æĮĤåľ¨
    -0.24
    gle
    -0.24
    iamond
    -0.24
    POSITIVE LOGITS
    SCO
    0.28
    óng
    0.27
    -Sah
    0.26
    å±ķå¼Ģ
    0.25
     Lines
    0.25
    Lines
    0.25
    ×ij×ķ×ĵ
    0.24
     CY
    0.23
    ç¦ģ
    0.23
    åħ±äº«
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.