© 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. 88410
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     shrink
    -0.29
    交æĺĵ
    -0.27
    ä¸Ģå¤Ħ
    -0.26
    åıĺè¿ģ
    -0.26
     capital
    -0.24
    -capital
    -0.24
    oris
    -0.24
    iny
    -0.24
     upt
    -0.24
    UGHT
    -0.24
    POSITIVE LOGITS
    è¾¾åĪ°
    0.24
    arbon
    0.24
    éĺµ
    0.23
    åĭĴ
    0.23
    ç»Ļ人
    0.23
    //****************************************************************************
    0.23
    Jer
    0.22
    Ali
    0.22
    uzzle
    0.22
    encode
    0.22
    Activations Density 0.009%

    No Known Activations