© 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. 19-TRANSCODER-HP
    7. 5356
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGC
    -0.27
    .hl
    -0.26
    plets
    -0.24
     asynchronously
    -0.23
    ás
    -0.23
     location
    -0.23
    agate
    -0.23
    ál
    -0.23
    天é¹ħ
    -0.22
     Bain
    -0.22
    POSITIVE LOGITS
    èµ°ä¸ĭåİ»
    0.25
    èĩĨ
    0.25
     transformations
    0.25
    ditor
    0.23
    çŁŃ
    0.23
    èµIJ
    0.23
    讨
    0.22
    å®ĹæŨ
    0.22
    è°ķ
    0.22
     therap
    0.22
    Activations Density 0.457%

    No Known Activations

    This feature has no known activations.