© 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. 97767
    Prev
    Next
    INDEX
    Explanations

    mode

    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
     tai
    -0.29
    å¿ĺ
    -0.27
    亿åIJ¨
    -0.26
    è¯Ħ为
    -0.25
     democracy
    -0.24
    iable
    -0.24
    è£Ļ
    -0.24
    èĢ½
    -0.23
    lected
    -0.23
    .SEVER
    -0.23
    POSITIVE LOGITS
    迫使
    0.60
    ä¿ĥ使
    0.48
    被迫
    0.47
    éĢ¼
    0.44
     forced
    0.42
     necess
    0.42
    ä¸įå¾Ĺä¸į
    0.41
     forcing
    0.40
    ä¸įå¾Ĺå·²
    0.38
     Forced
    0.38
    Activations Density 0.003%

    No Known Activations