© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4972
    Prev
    Next
    INDEX
    Explanations

    Bitcoin and code copyrights

    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
    å¿ħè¦ģ
    -0.27
     reflexivity
    -0.26
    æŁĵ
    -0.25
    åĴ¬
    -0.25
    æĢ»ä»·
    -0.25
     PROGMEM
    -0.24
    ivation
    -0.24
    æķĻ室
    -0.24
    ç©·
    -0.24
    etz
    -0.23
    POSITIVE LOGITS
    俶
    0.28
    ugins
    0.27
    åĩłåı¥
    0.27
    urch
    0.26
     patch
    0.25
    RIC
    0.25
    /Math
    0.25
    AAAA
    0.25
    _BRANCH
    0.24
     Branch
    0.24
    Activations Density 0.008%

    No Known Activations