© 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. 63193
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    好äºĭ
    -0.27
    ais
    -0.27
     Jou
    -0.26
    ","");↵
    -0.26
    Selector
    -0.26
    ãģ¤ãģĭ
    -0.25
    çĿĢ
    -0.25
    thro
    -0.24
    èĢ»
    -0.24
    éĥ½åºĶ该
    -0.24
    POSITIVE LOGITS
     survive
    0.25
    UCT
    0.24
    æįIJ
    0.24
    ublisher
    0.24
    ä¹ĭä½ľ
    0.24
    çĴĺ
    0.24
    _dur
    0.24
    contre
    0.23
    (py
    0.23
    æ´»ä¸ĭåİ»
    0.23
    Activations Density 15.893%

    No Known Activations

    This feature has no known activations.