© 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. 108277
    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
    éal
    -0.28
    ç§įç§į
    -0.26
    antas
    -0.25
     iov
    -0.25
    æŁIJç§įç¨ĭ度
    -0.25
    çİ°å®ŀä¸Ń
    -0.24
    çİ°å®ŀ
    -0.24
    æķĻæ¡Ī
    -0.24
    uss
    -0.24
    CPP
    -0.24
    POSITIVE LOGITS
    _CID
    0.26
    å´ĩé«ĺ
    0.26
    ETER
    0.26
    ãĥĩãĤ£ãĥ³ãĤ°
    0.24
    UPDATED
    0.24
    oped
    0.24
    oked
    0.24
    ä¸ĵ
    0.24
    KeyId
    0.24
     TSR
    0.24
    Activations Density 3.091%

    No Known Activations

    This feature has no known activations.