© 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. 5900
    Prev
    Next
    INDEX
    Explanations

    giant

    np_max-act · gemini-2.0-flash
    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
    itional
    -0.28
     lạc
    -0.25
    [sub
    -0.24
    好æĦŁ
    -0.24
    west
    -0.24
    è¿Ļ个人
    -0.23
    好转
    -0.23
    æĹłéļľç¢į
    -0.23
    vi
    -0.23
    bed
    -0.23
    POSITIVE LOGITS
     Ones
    0.26
    omet
    0.26
     ones
    0.24
    ieur
    0.23
    gom
    0.22
    hood
    0.22
    åıijæĺİ
    0.22
    碼
    0.22
     brass
    0.22
    ást
    0.22
    Activations Density 0.635%

    No Known Activations