© 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. 5353
    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
     konk
    -0.28
    渺
    -0.28
    lescope
    -0.26
    idot
    -0.26
     extinct
    -0.25
     bosses
    -0.25
    è§ħ
    -0.24
    æĺ¯å¾Ī
    -0.23
    磫
    -0.23
    +"'
    -0.23
    POSITIVE LOGITS
    .Surface
    0.28
    енÑĤа
    0.27
    scala
    0.26
    车åİ¢
    0.25
    pto
    0.25
    bes
    0.25
     “[
    0.25
    toupper
    0.24
    ackle
    0.24
    ature
    0.24
    Activations Density 1.212%

    No Known Activations

    This feature has no known activations.