© 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. 7621
    Prev
    Next
    INDEX
    Explanations

    scientific writing

    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
    çī¹åĪ«å£°æĺİ
    -0.27
    íħĮ
    -0.26
     CALLBACK
    -0.26
     Hooks
    -0.25
    -HT
    -0.24
    念
    -0.24
    å¾Ģå¤ĸ
    -0.24
     Palin
    -0.23
    ocked
    -0.23
    >Show
    -0.23
    POSITIVE LOGITS
    åİħ
    0.29
     standard
    0.28
    ient
    0.28
    å°½
    0.28
     due
    0.27
    ãģ»ãģ©
    0.27
     er
    0.25
    æłĩåĩĨ
    0.25
     final
    0.24
    å°Ĭ
    0.24
    Activations Density 0.221%

    No Known Activations