© 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. 63094
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĸĽ
    -0.26
    ipt
    -0.26
    èĻŀ
    -0.25
    ioc
    -0.25
    IPC
    -0.25
    itta
    -0.24
    prüf
    -0.24
     Frm
    -0.23
    èĤ¥èĥĸ
    -0.23
    TestMethod
    -0.23
    POSITIVE LOGITS
    plash
    0.26
    åĨ³çŃĸ
    0.26
    deb
    0.25
    è¿ĻäºĽéĹ®é¢ĺ
    0.24
     indexed
    0.24
    _Channel
    0.24
    ine
    0.24
    erset
    0.23
    agine
    0.23
    è·Łéļı
    0.23
    Activations Density 4.918%

    No Known Activations

    This feature has no known activations.