© 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. 107264
    Prev
    Next
    INDEX
    Explanations

    Technology and online business

    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
    norm
    -0.27
    orta
    -0.25
    allo
    -0.24
    (norm
    -0.24
     norm
    -0.24
    acies
    -0.24
    åIJĦæł·
    -0.24
    -shot
    -0.24
    .script
    -0.23
    otypes
    -0.23
    POSITIVE LOGITS
    æ´»
    0.24
    满æĦı度
    0.24
     Sloan
    0.24
    éĵİ
    0.24
    æĿ¡çº¦
    0.24
    髽
    0.23
     surroundings
    0.23
    ä¸ģ
    0.23
    _TUN
    0.23
    ÑĢÑĥж
    0.23
    Activations Density 3.214%

    No Known Activations