© 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. 5726
    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
    ed
    -0.32
     supply
    -0.28
    zier
    -0.27
    åIJİèĢħ
    -0.27
    çĭŃ
    -0.26
    ãĤ¸ãĤ§
    -0.26
    urgeon
    -0.26
    _git
    -0.26
    _complete
    -0.26
     receipt
    -0.25
    POSITIVE LOGITS
    htar
    0.28
    books
    0.26
    åĨħ马
    0.25
    еÑģÑĤво
    0.25
    为主ä½ĵ
    0.24
    elope
    0.24
    roma
    0.24
    antro
    0.24
     AO
    0.24
     Scor
    0.23
    Activations Density 0.330%

    No Known Activations

    This feature has no known activations.