© 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. 39553
    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
    itarian
    -0.33
    æĪijåİ»
    -0.25
    æĪijè¿ĺ
    -0.25
    æĪijæĬĬ
    -0.24
    -letter
    -0.23
    olle
    -0.23
    دÙħ
    -0.23
    -process
    -0.23
    -than
    -0.23
    -o
    -0.23
    POSITIVE LOGITS
    HeaderValue
    0.26
    大å¥ĸ
    0.24
     qualify
    0.24
    æĸ½èĤ¥
    0.24
    ç±į
    0.23
    software
    0.23
    onne
    0.23
     RaisePropertyChanged
    0.23
     espos
    0.23
    ä¸įåĪ°
    0.22
    Activations Density 0.139%

    No Known Activations

    This feature has no known activations.