© 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. 162300
    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
    ague
    -0.32
     tid
    -0.30
    ObjectId
    -0.27
    abus
    -0.26
    èIJ½
    -0.26
    æĹĥ
    -0.24
    aviest
    -0.24
    起身
    -0.24
    Client
    -0.24
    æīįåı¯ä»¥
    -0.24
    POSITIVE LOGITS
     Hond
    0.28
    ,idx
    0.27
    @brief
    0.26
    "indices
    0.26
    ilib
    0.26
    æİĮ
    0.25
    blade
    0.25
    .idx
    0.25
    ldata
    0.25
     nodeList
    0.25
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.