© 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. 12-TRANSCODER-HP
    7. 22717
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rike
    -0.28
    ä¹ħ
    -0.28
    IID
    -0.27
    andering
    -0.27
    æīĺ管
    -0.26
    è°
    -0.26
     idle
    -0.25
     shortfall
    -0.25
    hk
    -0.24
    é¢Ħæµĭ
    -0.24
    POSITIVE LOGITS
    lemen
    0.27
    èĤ²
    0.27
    éħĿ
    0.25
    etros
    0.25
    atro
    0.24
     prism
    0.24
    ilet
    0.24
    ä¸ĭä¸Ģ
    0.24
     jednÄħ
    0.23
    æ°ª
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.