© 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. 18-TRANSCODER-HP
    7. 88871
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    代表
    -0.28
    å¾ĹäºĨ
    -0.25
     representative
    -0.24
    éĢļè¿ĩ对
    -0.24
    ä¼ļ对
    -0.24
    +(\
    -0.23
    社ä¼ļ
    -0.23
    åħ¶æīĢ
    -0.23
    æ¯ķä¸ļåIJİ
    -0.23
    eworld
    -0.23
    POSITIVE LOGITS
    æ¼ıæ°´
    0.28
    å¾Ģåīį
    0.27
    ea
    0.26
     councils
    0.25
    å¾Ģå¤ĸ
    0.25
    ause
    0.24
    å¾Ģä¸ĭ
    0.24
    ç¼İ
    0.24
    ROL
    0.24
    olle
    0.24
    Activations Density 0.076%

    No Known Activations

    This feature has no known activations.