© 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. 107088
    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
    igm
    -0.31
    æ³Ķ
    -0.28
     errorCallback
    -0.28
    éĭª
    -0.27
    IGIN
    -0.26
     Kingston
    -0.26
     truth
    -0.25
    åĪĨ彩
    -0.25
     tumor
    -0.25
     honored
    -0.24
    POSITIVE LOGITS
    追踪
    0.32
    æİī
    0.32
    代表
    0.32
    éĻ¤äºĨ
    0.31
    æłĩçļĦ
    0.31
    订
    0.30
    è·Łè¸ª
    0.30
    çģµ
    0.30
    æĪIJ
    0.30
    å°¾
    0.29
    Activations Density 1.409%

    No Known Activations

    This feature has no known activations.