© 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. 19-TRANSCODER-HP
    7. 9155
    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
    nev
    -0.30
    è§ģè¯ģ
    -0.28
    undy
    -0.28
    UniqueId
    -0.26
    åĽłä¸ºå¥¹
    -0.26
    letics
    -0.26
    çĩ¥
    -0.25
    ä¾Ľåħ»
    -0.25
    åıijçĶŁ
    -0.25
    èĪĦ
    -0.25
    POSITIVE LOGITS
    -terminal
    0.27
    éķĹ
    0.26
    atable
    0.26
    mia
    0.25
    aptor
    0.24
    terminal
    0.24
    鲸
    0.24
    stag
    0.24
     perfect
    0.24
    ))-
    0.23
    Activations Density 0.036%

    No Known Activations

    This feature has no known activations.