© 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. 22-TRANSCODER-HP
    7. 87954
    Prev
    Next
    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bite
    -0.27
     therein
    -0.27
    æŁIJæŁIJ
    -0.27
    两个维æĬ¤
    -0.26
    /dataTables
    -0.26
    =https
    -0.25
    .BufferedReader
    -0.24
    è°Ĺ
    -0.24
    -master
    -0.24
     somebody
    -0.24
    POSITIVE LOGITS
    æĺ¨æĹ¥
    0.39
    æĺ¨
    0.37
    æĺ¨å¤©
    0.34
    è¿ijæĹ¥
    0.30
    çł´
    0.30
    éĢ¾
    0.28
    æľ¬åij¨
    0.28
    ä»Ĭ
    0.28
    åĿļ
    0.27
    æľ¬æĬ¥
    0.27
    Activations Density 0.109%

    No Known Activations