© 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. 6802
    Prev
    Next
    INDEX
    Explanations

    AY

    np_max-act · gemini-2.0-flash
    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
    ãģ¾ãģĦ
    -0.30
    å°ıçĻ½
    -0.29
    åħ¶æ¬¡æĺ¯
    -0.27
    ||
    -0.26
    饿
    -0.24
    ENC
    -0.24
     subject
    -0.24
    åħ¶æ¬¡
    -0.24
    å¼Ģ头
    -0.24
    held
    -0.24
    POSITIVE LOGITS
     Patt
    0.26
    strup
    0.25
    çĹĤ
    0.24
    _bonus
    0.23
    veral
    0.23
    -touch
    0.23
     Brah
    0.23
    olut
    0.22
    olon
    0.22
     onFinish
    0.22
    Activations Density 0.018%

    No Known Activations