© 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. 5416
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     Äijiá»ģu
    -0.27
    /Area
    -0.27
    Ñīи
    -0.27
    åºĹéĩĮ
    -0.25
    AFP
    -0.25
     Draw
    -0.25
    Together
    -0.25
     dearly
    -0.24
    VERN
    -0.24
    inke
    -0.24
    POSITIVE LOGITS
    sql
    0.28
    amble
    0.27
    åĨ²
    0.26
    为主
    0.26
     Nicholson
    0.25
    æ²ĸ
    0.25
     "+↵
    0.24
     sql
    0.24
     SQL
    0.24
     ballpark
    0.24
    Activations Density 0.034%

    No Known Activations