© 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. 109151
    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
    裸
    -0.31
     Backbone
    -0.28
     openness
    -0.26
    ÙĪØ°
    -0.25
    Cons
    -0.25
     Yosh
    -0.24
    é»Ħèī²
    -0.24
    bservice
    -0.24
     Synopsis
    -0.24
    头顶
    -0.24
    POSITIVE LOGITS
     reiterated
    0.26
    ìĤ¬ìĿ´íĬ¸
    0.26
    åı¦ä¸Ģè¾¹
    0.26
    åĪĨä¼ļ
    0.26
    主é¡Į
    0.25
     protester
    0.25
    axon
    0.24
    åĵģçīĮçļĦ
    0.24
    ç¢ĩ
    0.23
    wers
    0.23
    Activations Density 0.177%

    No Known Activations

    This feature has no known activations.