© 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. 22-TRANSCODER-HP
    7. 130358
    Prev
    Next
    INDEX
    Explanations

    Computer/internet related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    goto
    -0.29
    foy
    -0.28
    CAC
    -0.28
    侯
    -0.24
    ablish
    -0.24
    åħ¬åı¸å°Ĩ
    -0.24
    为空
    -0.23
    :@
    -0.23
    OBJ
    -0.23
    /Framework
    -0.23
    POSITIVE LOGITS
    atives
    0.32
     ideal
    0.27
    thal
    0.24
     interactive
    0.24
     bookmarks
    0.23
    (("
    0.23
    orn
    0.23
    æĴIJ
    0.23
    ãģĿãģĨãģ§
    0.23
    çIJĨæĥ³
    0.22
    Activations Density 0.013%

    No Known Activations