© 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. 8074
    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
    ä¸įä¸ĭ
    -0.29
    lad
    -0.26
    çĪµ
    -0.24
     Gate
    -0.24
     Stealth
    -0.24
     switch
    -0.24
    -hidden
    -0.23
    çĸıæķ£
    -0.23
    -seat
    -0.23
    ä¸įä¿¡
    -0.23
    POSITIVE LOGITS
    Cold
    0.26
    quired
    0.26
    æ¼Ķ
    0.25
     froze
    0.25
    cold
    0.25
     evolves
    0.24
    顾
    0.24
    ä¹Łä¸įéĶĻ
    0.24
    odon
    0.23
    羣å®ŀçļĦ
    0.23
    Activations Density 0.050%

    No Known Activations

    This feature has no known activations.