© 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. 39551
    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
    è®°å¾Ĺ
    -0.33
     always
    -0.30
    éļıæŶéļı
    -0.29
    ä¸Ģä¼ļåĦ¿
    -0.29
    å¤Ħå¤Ħ
    -0.28
    æļ´
    -0.27
    åĩ¡äºĭ
    -0.27
     hÆ°á»Łng
    -0.27
    æŁĶåĴĮ
    -0.27
    å¿ĥçĸ¼
    -0.26
    POSITIVE LOGITS
     tweeted
    0.31
     ÑģамоÑģÑĤоÑı
    0.29
     researching
    0.28
    ruz
    0.25
    çį¨ç«ĭ
    0.24
    agna
    0.24
    émon
    0.23
     research
    0.23
    ivas
    0.23
     embarked
    0.23
    Activations Density 0.061%

    No Known Activations

    This feature has no known activations.