© 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. 6623
    Prev
    Next
    INDEX
    Explanations

    Data sampling

    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
     accru
    -0.29
    igan
    -0.28
    inement
    -0.27
    æĶ¶æķĽ
    -0.26
    ä»ĸåľ¨
    -0.25
    blers
    -0.24
     Nicholson
    -0.24
    æĦı大
    -0.24
    ailer
    -0.24
     Trib
    -0.24
    POSITIVE LOGITS
    æīĵåħ¥
    0.29
    åĩºæĿ¥
    0.27
    åĩºæĿ¥çļĦ
    0.26
    Docs
    0.25
     converts
    0.25
    -src
    0.24
    à¹ģหละ
    0.24
    ä¸Ģå±Ĥ
    0.24
    _consts
    0.24
     celebrate
    0.23
    Activations Density 0.023%

    No Known Activations