© 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. 63914
    Prev
    Next
    INDEX
    Explanations

    Encoding/Programming

    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
    acre
    -0.30
    eness
    -0.27
    èµ·äºĨ
    -0.26
    imin
    -0.26
    ertools
    -0.25
    ä¸ĢéĿ¢
    -0.25
    èĥ½è¾¾åĪ°
    -0.24
    aptors
    -0.24
    onymous
    -0.24
    æĭĽ
    -0.24
    POSITIVE LOGITS
     set
    0.30
     unit
    0.28
    åħ¶å®ŀ
    0.26
     quasi
    0.25
    åįķåħĥ
    0.25
     over
    0.24
     translated
    0.24
     actual
    0.24
    .protobuf
    0.24
    庵
    0.23
    Activations Density 1.398%

    No Known Activations