© 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. 5287
    Prev
    Next
    INDEX
    Explanations

    beginnings of life

    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
    arter
    -0.31
    ä»·
    -0.28
     Construct
    -0.28
    etag
    -0.27
     constructs
    -0.27
    ToFront
    -0.26
     Constructs
    -0.26
    æĪijåĸľæ¬¢
    -0.26
     Layer
    -0.25
     construct
    -0.25
    POSITIVE LOGITS
    .binding
    0.29
    undef
    0.28
     unconditional
    0.26
    cee
    0.26
     unborn
    0.25
    èĢģçīĮ
    0.25
    Tot
    0.25
     pitched
    0.24
    :hidden
    0.24
    çļĦ第ä¸Ģ
    0.24
    Activations Density 0.005%

    No Known Activations