© 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. 63302
    Prev
    Next
    INDEX
    Explanations

    academic/research writing

    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
    大æĸ¹
    -0.28
    ä¸ļ
    -0.25
    emens
    -0.25
    ipse
    -0.25
    å·¦åı³
    -0.25
    :black
    -0.25
    addin
    -0.24
    èŁĨ
    -0.24
    ButtonType
    -0.24
    -Za
    -0.24
    POSITIVE LOGITS
    代
    0.28
    æĸ¹æīį
    0.28
    åĩłå¼ł
    0.28
    ä¸Ģå¼ł
    0.27
    çªģåĩºéĹ®é¢ĺ
    0.25
     darn
    0.25
    ATERIAL
    0.24
    IRO
    0.24
    ead
    0.24
    顶éĥ¨
    0.24
    Activations Density 37.315%

    No Known Activations