© 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. 9217
    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
     ani
    -0.26
    大åĪĩ
    -0.26
    roe
    -0.24
     Equip
    -0.24
    FLAGS
    -0.23
    å±Ĭ
    -0.23
    ib
    -0.23
    ê´Ģ
    -0.23
    intern
    -0.23
    åľ°è²Į
    -0.23
    POSITIVE LOGITS
    abouts
    0.28
    ä¸į满æĦı
    0.27
    among
    0.24
     bothers
    0.24
    彤
    0.24
    ego
    0.24
    æī¹è¯Ħ
    0.24
    æĿijéķĩ
    0.24
    åħ¶ä¸Ń
    0.23
    æĦı
    0.23
    Activations Density 0.101%

    No Known Activations

    This feature has no known activations.