© 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. 98356
    Prev
    Next
    INDEX
    Explanations

    Code/technical documents

    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
    æĦŁæŁĵèĢħ
    -0.30
    åĬĽåº¦
    -0.29
    é«ĺ涨
    -0.28
    å¹ħ度
    -0.27
    æĢ»éĩı
    -0.27
    ä¸įæĢķ
    -0.27
    é¢ĦæľŁ
    -0.27
    عاÙĨ
    -0.26
    antity
    -0.26
     threatened
    -0.26
    POSITIVE LOGITS
    精确
    0.50
     precise
    0.42
    åĩĨç¡®
    0.42
    ç²¾åĩĨ
    0.42
     detailed
    0.40
    ç²¾å¯Ĩ
    0.40
    å¤įæĿĤ
    0.38
    ละà¹Ģà¸Ń
    0.38
    _precision
    0.37
     intricate
    0.36
    Activations Density 0.001%

    No Known Activations