© 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. 5929
    Prev
    Next
    INDEX
    Explanations

    Learning and instruction

    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
    опеÑĢ
    -0.27
    +',
    -0.27
    alog
    -0.27
    atars
    -0.27
    éĩįå·¥
    -0.27
    "](
    -0.26
     giả
    -0.25
    ”ãĢĤ
    -0.25
    soles
    -0.25
    åħ»èĢģ
    -0.24
    POSITIVE LOGITS
    mit
    0.29
     desn
    0.27
    imity
    0.26
     Most
    0.25
    xFFFFFFFF
    0.24
    omic
    0.24
     Huge
    0.24
    Most
    0.24
    èħIJ
    0.24
    éĻ¤éĿŀ
    0.24
    Activations Density 0.004%

    No Known Activations