© 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. 129548
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    æĬ½
    -0.28
    åĶ®åIJİ
    -0.27
    ||
    -0.26
     bell
    -0.26
    åĸ»
    -0.25
    _recv
    -0.25
     hasattr
    -0.25
     sque
    -0.25
    rror
    -0.24
    çİ°å®ŀä¸Ń
    -0.24
    POSITIVE LOGITS
    cling
    0.29
    年以æĿ¥
    0.29
    åı¤èĢģçļĦ
    0.26
    zos
    0.26
    ENE
    0.26
     Petty
    0.25
    æķ°åŃĹè´§å¸ģ
    0.25
    缴è¾ĸå¸Ĥ
    0.24
    enez
    0.24
    ewish
    0.24
    Activations Density 8.110%

    No Known Activations