© 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. 22-TRANSCODER-HP
    7. 112249
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itate
    -0.29
     Dil
    -0.24
    ä¸Ģ天
    -0.24
    é¡»
    -0.23
    edback
    -0.23
     Consult
    -0.23
    ByKey
    -0.23
    .Attribute
    -0.22
    Gas
    -0.22
    ,cv
    -0.22
    POSITIVE LOGITS
    管çIJĨæĿ¡ä¾ĭ
    0.26
    rapper
    0.23
    åģľçīĮ
    0.23
    輩
    0.23
    ä¿¡ç®±
    0.23
    礴
    0.23
    ostream
    0.23
    ç²¹
    0.23
     UB
    0.22
     manned
    0.22
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.