© 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. 6645
    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
    çļĩåĨł
    -0.26
    æĹ¥äº§
    -0.26
    tract
    -0.26
    æŃ»èĢħ
    -0.26
    åī¯æľ¬
    -0.25
    çĶŁæŃ»
    -0.25
    åį´åıijçİ°
    -0.25
     warmed
    -0.25
    enedor
    -0.25
    ãģ§ãģįãģŁ
    -0.24
    POSITIVE LOGITS
     bay
    0.26
     thụ
    0.26
    Att
    0.26
    _att
    0.25
     Banc
    0.25
    湫
    0.25
    å®ļ
    0.24
    .items
    0.24
    iid
    0.24
     irq
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.