© 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. 9314
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -inline
    -0.27
    ä¸ij
    -0.26
     deport
    -0.25
    åĩłå¼ł
    -0.25
    _CAST
    -0.25
    åĪĨåĪ«æĺ¯
    -0.25
    copyright
    -0.25
    âĸ²
    -0.24
     Dad
    -0.24
    御
    -0.24
    POSITIVE LOGITS
    æ§Į
    0.28
    бÑĥ
    0.27
    лиÑģÑĤ
    0.25
    âį¨
    0.25
    æ±Łå±±
    0.24
    é¢ijéģĵ
    0.24
    ç½®æį¢
    0.24
    骨头
    0.24
    æįŁä¼¤
    0.24
     mÅĤ
    0.24
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.