© 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. 39753
    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
     Lar
    -0.28
    eur
    -0.24
     aup
    -0.24
    fulness
    -0.24
    åĪ°ä½į
    -0.24
    ä¸ĸçķĮ级
    -0.23
    è¾¹çķĮ
    -0.23
    ç©°
    -0.23
    èĴ¿
    -0.23
    егод
    -0.23
    POSITIVE LOGITS
    ves
    0.30
     tem
    0.29
    _ALIAS
    0.26
     DSL
    0.26
     rest
    0.26
     module
    0.24
    妻
    0.24
    _Init
    0.24
     sim
    0.23
     part
    0.23
    Activations Density 50.392%

    No Known Activations

    This feature has no known activations.