© 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. 40184
    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
    /cards
    -0.25
    ,callback
    -0.24
    /List
    -0.23
     ÃŃch
    -0.23
     DateFormatter
    -0.23
    /Form
    -0.23
    ,to
    -0.23
    atel
    -0.22
     Advantage
    -0.22
     LayoutInflater
    -0.22
    POSITIVE LOGITS
    çī¹åĪ«
    0.32
    çī¹åĪ¥
    0.29
    quam
    0.24
    å¿Ļ
    0.24
    quiv
    0.24
    å£
    0.24
    asis
    0.23
     pubb
    0.23
     particularly
    0.23
    çĸ²
    0.23
    Activations Density 40.404%

    No Known Activations

    This feature has no known activations.