© 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. 35-TRANSCODER-HP
    7. 39863
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åłij
    -0.28
    èĥĤ
    -0.27
    /conf
    -0.26
    -League
    -0.26
    umen
    -0.25
    GOR
    -0.25
     AppModule
    -0.25
    è¿ĩ大
    -0.24
    æĭĴ
    -0.24
    让æĤ¨
    -0.24
    POSITIVE LOGITS
    fram
    0.28
    edList
    0.25
    -list
    0.25
    L
    0.24
    鼨
    0.24
    ing
    0.24
    itespace
    0.23
    mi
    0.23
    ä¾¿å®ľ
    0.23
    etwork
    0.23
    Activations Density 45.013%

    No Known Activations

    This feature has no known activations.