© 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. 64443
    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
     midway
    -0.27
    ä¸Ģè½®
    -0.26
    -half
    -0.26
    ä¾¿å®ľ
    -0.26
    ungi
    -0.25
    .middle
    -0.25
    éªijè¡Į
    -0.25
    mid
    -0.25
    åıijå±ķä¸Ń
    -0.25
    å¤ĸ表
    -0.25
    POSITIVE LOGITS
    çĽ²
    0.31
    ç²¾
    0.28
     Functions
    0.28
    reature
    0.26
    åѤ
    0.26
    è¿ĩçļĦ
    0.25
    请èģĶç³»
    0.25
    adena
    0.24
    æĭ¾
    0.24
     FUNCTIONS
    0.23
    Activations Density 6.561%

    No Known Activations

    This feature has no known activations.