© 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. 64408
    Prev
    Next
    INDEX
    Explanations

    questions and instructions

    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
    åı¦ä¸Ģ
    -0.25
    è·Ŀ
    -0.25
    ãģ£ãģ¡ãĤĥ
    -0.24
    oning
    -0.24
    åı¦ä¸Ģ个
    -0.24
    åı¦å¤ĸä¸Ģ个
    -0.24
    çļĦæĵįä½ľ
    -0.24
     newest
    -0.23
     immune
    -0.23
    åı¦ä¸Ģè¾¹
    -0.23
    POSITIVE LOGITS
    oyer
    0.28
    Fore
    0.28
    ported
    0.26
    gro
    0.26
    tle
    0.25
    满æĦıçļĦ
    0.24
    LAY
    0.24
    tl
    0.24
    éĿŀ常åĸľæ¬¢
    0.24
    å¼Ģåľº
    0.24
    Activations Density 5.289%

    No Known Activations