© 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. 98229
    Prev
    Next
    INDEX
    Explanations

    possibility

    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
    åIJĮåŁİ
    -0.30
     xuyên
    -0.25
    åIJ¯åıij
    -0.25
    -0.25
    æĮĩ
    -0.25
    iner
    -0.25
     Somebody
    -0.24
    —is
    -0.24
    帮åĬ©ä¼ģä¸ļ
    -0.24
     Laud
    -0.24
    POSITIVE LOGITS
     yourself
    0.32
     yourselves
    0.31
    注æĦıåĪ°
    0.24
    è¿ĵ
    0.24
    uhan
    0.24
     Break
    0.24
     Ting
    0.24
    纡
    0.24
    åĨ»
    0.23
     noticed
    0.23
    Activations Density 0.075%

    No Known Activations