© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 221
    Prev
    Next
    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸¥æł¼èIJ½å®ŀ
    -0.25
    åĪĨæµģ
    -0.25
    æİ¥åĪ°
    -0.25
    ä¸ĭæĿ¥
    -0.24
    cludes
    -0.24
    >/<
    -0.24
    setattr
    -0.24
    éĻ¤
    -0.24
    ARN
    -0.24
    èĩªå¾ĭ
    -0.24
    POSITIVE LOGITS
     THEIR
    0.26
    麽
    0.25
     Their
    0.24
    åĭģ
    0.24
    intage
    0.24
    çħ²
    0.24
    麼
    0.23
     enterprise
    0.23
     Enterprise
    0.23
    ubes
    0.23
    Activations Density 0.208%

    No Known Activations