© 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. 5342
    Prev
    Next
    INDEX
    Explanations

    often

    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
     farewell
    -0.27
     mógÅĤ
    -0.25
    çŁŃæŶéĹ´åĨħ
    -0.24
    æł¹æį®èĩªå·±
    -0.23
    个交æĺĵ
    -0.23
    èµĸ以
    -0.23
    è¿Ļä¸ī个
    -0.23
    åĪ«çļĦ
    -0.23
    ìĿĮìĿĦ
    -0.23
     added
    -0.23
    POSITIVE LOGITS
     >&
    0.27
    chè
    0.26
    ditor
    0.26
    Assoc
    0.25
    dance
    0.25
    ihil
    0.25
    ãģĵãģ¨ãģ«
    0.24
    legant
    0.24
    füg
    0.23
    setError
    0.23
    Activations Density 0.070%

    No Known Activations