© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 38607
    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
    Negative Logits
    ).
    -0.26
    å°ijæķ°
    -0.25
    çĪ¨
    -0.25
     stimulate
    -0.24
     contacto
    -0.24
    è¡Ĺ
    -0.24
     sir
    -0.24
    æݥ触
    -0.23
     bastante
    -0.23
    yas
    -0.23
    POSITIVE LOGITS
    æī¾åĪ°
    0.30
    èįĴ
    0.30
     Finder
    0.26
    (Messages
    0.26
    误
    0.25
     ÑĩаÑģов
    0.25
    prev
    0.24
    omers
    0.24
    iever
    0.24
    setUp
    0.24
    Activations Density 0.840%

    No Known Activations

    This feature has no known activations.