© 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. 27-TRANSCODER-HP
    7. 57825
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    趣
    -0.31
    çµ®
    -0.28
    èİŀ
    -0.28
     Fun
    -0.27
     dare
    -0.26
     Wr
    -0.26
    趣åij³
    -0.26
    éŁª
    -0.26
     FUN
    -0.26
    çĥŃçĤ¹
    -0.26
    POSITIVE LOGITS
    人éĢī
    0.30
     epidemic
    0.29
    quine
    0.29
    ä¾µåįł
    0.26
    elps
    0.26
    çĻ¾åĪĨä¹ĭ
    0.26
    èĭŁ
    0.26
    hausen
    0.26
    jang
    0.25
     helf
    0.25
    Activations Density 0.000%

    No Known Activations