© 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. 5821
    Prev
    Next
    INDEX
    Explanations

    mixed text/code excerpts

    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
     Vine
    -0.28
    ä¸įæĩĤ
    -0.27
    xFFFF
    -0.27
    äºĭåIJİ
    -0.27
    inde
    -0.26
    going
    -0.26
     difference
    -0.25
    unched
    -0.25
     differences
    -0.25
    -called
    -0.25
    POSITIVE LOGITS
    åIJ«ãģ¾ãĤĮ
    0.25
    èļķ
    0.24
     INCLUDED
    0.23
    ourke
    0.23
    åĮħåIJ«äºĨ
    0.23
    楼
    0.23
     contained
    0.23
    éĿ
    0.23
     unp
    0.23
     branding
    0.22
    Activations Density 0.022%

    No Known Activations