© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8864
    Prev
    Next
    INDEX
    Explanations

    programming and justice

    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
    alm
    -0.30
    被æĬĵ
    -0.26
     account
    -0.25
    ieri
    -0.24
    åıªä¸º
    -0.24
    ³³³³³³³³
    -0.24
    yd
    -0.24
    滨å·ŀ
    -0.24
    adel
    -0.24
    chter
    -0.24
    POSITIVE LOGITS
    æİ·
    0.28
    Capability
    0.27
    åĵªæĢķæĺ¯
    0.26
    ãģ¾ãģĹãģ¦
    0.26
    è´´å¿ĥ
    0.25
    à¤Ĩ
    0.25
    åįģ个
    0.24
    ÑģÑħем
    0.24
     schemas
    0.23
     competitiveness
    0.23
    Activations Density 0.007%

    No Known Activations