© 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. 39268
    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
    èIJ½å®ŀ
    -0.29
    æµĶ
    -0.26
    éļ°
    -0.25
     Rent
    -0.25
    yt
    -0.25
    çŁ³èĨı
    -0.25
    illon
    -0.24
    ption
    -0.23
    idend
    -0.23
    fulness
    -0.23
    POSITIVE LOGITS
    ahir
    0.24
    欲ãģĹãģĦ
    0.23
     encodeURIComponent
    0.23
     become
    0.22
    FACT
    0.22
    /generated
    0.22
     aren
    0.22
    oshi
    0.22
    ftware
    0.22
    linear
    0.21
    Activations Density 59.777%

    No Known Activations

    This feature has no known activations.