© 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. 63356
    Prev
    Next
    INDEX
    Explanations

    Acronyms and abbreviations

    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
    Bounds
    -0.26
    举æĬ¥
    -0.25
    注æĦıåĪ°
    -0.25
    éĿ¢ä¸Ĭ
    -0.24
     onSave
    -0.24
     normally
    -0.24
    setAttribute
    -0.24
    æĭľå¸Ī
    -0.24
    usses
    -0.24
    Poll
    -0.23
    POSITIVE LOGITS
    agan
    0.31
    åĬ©
    0.30
    éĻį
    0.27
    rah
    0.26
    back
    0.26
    bc
    0.26
    å·¦
    0.24
    ottage
    0.24
    unge
    0.24
    bk
    0.24
    Activations Density 83.080%

    No Known Activations