© 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. 40242
    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
     háºŃu
    -0.26
    itic
    -0.26
     Bag
    -0.26
    issors
    -0.25
    Bag
    -0.25
    ixa
    -0.25
    大æĸ¹
    -0.24
    -publish
    -0.24
    arus
    -0.24
    _IA
    -0.24
    POSITIVE LOGITS
    RICS
    0.28
    表彰
    0.24
    æ¿Ģæ´»
    0.23
    ael
    0.23
    Marshal
    0.22
    对æĸ¹
    0.22
    æ¾į
    0.22
     modeled
    0.22
     drinks
    0.22
     fabs
    0.22
    Activations Density 2.982%

    No Known Activations

    This feature has no known activations.