© 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. 8079
    Prev
    Next
    INDEX
    Explanations

    anded

    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
    æļĤ
    -0.38
     incomplete
    -0.36
    ä¸įå®Į
    -0.34
    Incomplete
    -0.34
     currently
    -0.34
    unfinished
    -0.34
     partial
    -0.33
    åĪ°çİ°åľ¨
    -0.33
     unfinished
    -0.32
    æļĤæŶ
    -0.32
    POSITIVE LOGITS
    RESH
    0.29
    ä¸Ģä¸ĭåŃIJ
    0.28
    egas
    0.27
    erce
    0.27
    iks
    0.26
     bored
    0.25
    errupt
    0.24
    çĶŁäº§åĬĽ
    0.24
    åĩºèº«
    0.24
    çŃĸçķ¥
    0.24
    Activations Density 0.227%

    No Known Activations