© 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. 39050
    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
    omore
    -0.27
    åĩĩ
    -0.27
    ä¸īæĿ¡
    -0.26
    luent
    -0.25
    utan
    -0.25
    èĬĤ
    -0.24
    sdale
    -0.24
     INDIRECT
    -0.24
    éķľå¤´
    -0.23
    è¯ķçĤ¹
    -0.23
    POSITIVE LOGITS
     rev
    0.28
    令人
    0.26
     dispos
    0.26
    ÙĨاÙĨ
    0.25
     rec
    0.24
    icc
    0.24
    ائØŃ
    0.24
    intr
    0.23
     prov
    0.23
    rev
    0.23
    Activations Density 0.813%

    No Known Activations

    This feature has no known activations.