© 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. 40338
    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
    æ³ł
    -0.27
    ASURE
    -0.26
    INGS
    -0.26
    宫
    -0.24
    isk
    -0.24
    Difference
    -0.24
    agem
    -0.24
     Difference
    -0.24
     hin
    -0.23
    ISK
    -0.23
    POSITIVE LOGITS
    es
    0.28
    åIJĮèĥŀ
    0.27
    æľĢç¾İçļĦ
    0.25
    áºŃu
    0.25
    è¿ĺå¾Ĺ
    0.24
    èĩªåıij
    0.24
    为æĪij们
    0.23
    ::::::
    0.23
    å°ıæŶåīį
    0.23
    é³IJ
    0.23
    Activations Density 3.931%

    No Known Activations

    This feature has no known activations.