© 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. 88614
    Prev
    Next
    INDEX
    Explanations

    Code and data snippets

    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
     correspond
    -0.25
    åİŁæĸĩåľ°åĿĢ
    -0.25
     Correspond
    -0.24
    èĪĪ趣
    -0.24
    å®ģåİ¿
    -0.24
    ibly
    -0.23
    bon
    -0.23
    łéĻ¤
    -0.23
     lifelong
    -0.23
    inyin
    -0.23
    POSITIVE LOGITS
    yre
    0.31
    第äºĮ
    0.27
    _DEFINITION
    0.27
    第ä¸ĢèĬĤ
    0.27
     inc
    0.26
    -License
    0.26
    èĮ«
    0.26
    arrival
    0.25
     Inc
    0.24
    éĥ¨
    0.24
    Activations Density 0.003%

    No Known Activations