© 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. 7306
    Prev
    Next
    INDEX
    Explanations

    scheduling and constraints

    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
     Mim
    -0.32
     mim
    -0.28
     painting
    -0.26
    模仿
    -0.26
    pan
    -0.25
    鹫
    -0.25
    åĪļ好
    -0.24
     pass
    -0.24
    otyp
    -0.24
    ([{
    -0.23
    POSITIVE LOGITS
    æīĴ
    0.28
     Kare
    0.27
    _goto
    0.26
     Wisdom
    0.26
    CAL
    0.24
     yyn
    0.24
    agar
    0.24
    çļĦæĶ¿æ²»
    0.24
    åıĭæĥħ
    0.24
    ä¹ĭæīĢ以
    0.24
    Activations Density 0.111%

    No Known Activations