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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141367
    Prev
    Next
    INDEX
    Explanations

    XML and Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĢĮ对äºİ
    -0.26
    elite
    -0.26
     callee
    -0.25
    åĩºç¤º
    -0.25
    ilit
    -0.25
    rü
    -0.25
    èĢĮçİ°åľ¨
    -0.24
     deserve
    -0.24
    å®ŀçİ°
    -0.24
    HandlerContext
    -0.24
    POSITIVE LOGITS
    otte
    0.29
     portion
    0.29
    iras
    0.27
    æİ£
    0.27
    JV
    0.26
    æĥ³èµ·æĿ¥
    0.26
    portion
    0.25
    ymes
    0.25
     portions
    0.24
    纨
    0.24
    Activations Density 0.519%

    No Known Activations