© 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. 25-TRANSCODER-HP
    7. 107403
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allot
    -0.26
    åijĬè¯ī
    -0.25
    空çĻ½
    -0.25
     amp
    -0.24
    ç²²
    -0.24
    /master
    -0.24
    è¦ıå®ļ
    -0.23
    æĬ½
    -0.23
    ãĤĪãģĨãģ«
    -0.23
    ää
    -0.23
    POSITIVE LOGITS
    èIJ¥åķĨçݯå¢ĥ
    0.27
     Lori
    0.25
     BASIS
    0.25
     Loy
    0.25
    scroll
    0.25
    对æѤ
    0.25
    æ»ļ
    0.24
    Scroll
    0.24
    paced
    0.24
    Scott
    0.24
    Activations Density 0.022%

    No Known Activations

    This feature has no known activations.