© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7271
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ga
    -0.35
     gauge
    -0.29
     Ga
    -0.28
     Pir
    -0.26
     copying
    -0.25
    oble
    -0.25
    ListNode
    -0.25
    ä¸ĢæīĢ
    -0.24
    ibu
    -0.24
     copied
    -0.24
    POSITIVE LOGITS
     Interested
    0.30
     expended
    0.26
    ä¸į认è¯Ĩ
    0.25
    isz
    0.25
    ',['
    0.25
    åĩºå¢ĥ
    0.24
    ä¼ļéĢīæĭ©
    0.24
    å½
    0.24
    èµĸ
    0.24
    Disp
    0.23
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.