© 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. 39491
    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
    æĹºçĽĽ
    -0.35
     Coul
    -0.28
    顶端
    -0.27
    æŀģèĩ´
    -0.25
     SSA
    -0.24
    å¤ļåľ°
    -0.24
    纯åĩĢ
    -0.24
    æľºèº«
    -0.24
    ç»Ŀä½³
    -0.24
    åIJĪæ³ķæĿĥçĽĬ
    -0.24
    POSITIVE LOGITS
    eli
    0.31
    cla
    0.27
    ibi
    0.27
    _BIG
    0.26
    ns
    0.25
    -ce
    0.25
    ark
    0.25
    enco
    0.25
    ibe
    0.25
    articles
    0.25
    Activations Density 37.392%

    No Known Activations

    This feature has no known activations.