© 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. 39733
    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
    ari
    -0.27
    ctest
    -0.26
    Team
    -0.24
    Fo
    -0.24
    isma
    -0.24
    Comp
    -0.24
    Component
    -0.24
    Contr
    -0.24
    IEL
    -0.24
    Strip
    -0.24
    POSITIVE LOGITS
    赦
    0.27
    å¾Ĺå¤ļ
    0.26
     mere
    0.25
     seldom
    0.25
     possession
    0.24
     Gründe
    0.24
    好转
    0.24
     ALS
    0.24
    æŁĦ
    0.23
    忽
    0.23
    Activations Density 21.142%

    No Known Activations

    This feature has no known activations.