© 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. 40131
    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
    NO
    -0.32
     Weed
    -0.29
     Wis
    -0.29
     Com
    -0.28
     Out
    -0.28
     Against
    -0.28
    No
    -0.28
     No
    -0.28
     Black
    -0.27
     Station
    -0.27
    POSITIVE LOGITS
    é²·
    0.29
    lyph
    0.26
    åįķ纯
    0.26
    spiel
    0.26
    ãģĶç´¹
    0.25
     -/↵
    0.25
     /^\
    0.25
    ãģĬãģĻãģĻ
    0.25
    åģ¶å°Ķ
    0.25
    _Impl
    0.25
    Activations Density 2.578%

    No Known Activations

    This feature has no known activations.