© 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. 87668
    Prev
    Next
    INDEX
    Explanations

    Code and legal disclaimers

    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
    iÄĩ
    -0.29
    æĦŁçŁ¥
    -0.28
    å¼
    -0.27
    å·®è·Ŀ
    -0.26
    nel
    -0.25
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.25
     combinations
    -0.25
    ç®Ģ约
    -0.25
    imary
    -0.24
    ilar
    -0.24
    POSITIVE LOGITS
    ntl
    0.28
    ick
    0.26
    åħįè´£
    0.26
    atee
    0.26
    ")+
    0.26
    Inflater
    0.26
    oten
    0.25
    æŁĵ
    0.25
     Tenn
    0.25
    ÑĤов
    0.25
    Activations Density 0.064%

    No Known Activations