© 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. 8156
    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
    å¿ĺè®°äºĨ
    -0.29
     <%=
    -0.28
    èĩªåľ¨
    -0.27
    thic
    -0.27
     Fits
    -0.25
    fen
    -0.25
    icer
    -0.25
    untas
    -0.24
    梯
    -0.24
    åı°
    -0.24
    POSITIVE LOGITS
    æķ
    0.26
     successfully
    0.25
    åı¸ä»¤
    0.25
    ival
    0.24
    å±ķåİħ
    0.24
     Reid
    0.24
    好转
    0.24
    å±ĭéĩĮ
    0.23
    instr
    0.23
    ikt
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.