© 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. 98005
    Prev
    Next
    INDEX
    Explanations

    the

    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
    hor
    -0.31
    çĴľ
    -0.25
    -ring
    -0.24
     Thom
    -0.24
    orical
    -0.24
    åľ¨éĩĮéĿ¢
    -0.23
    èIJ¥ä¸ļ
    -0.23
    åľ¨è¿Ļç§į
    -0.23
    è±
    -0.23
    ä¸Ģèµ·
    -0.23
    POSITIVE LOGITS
    岫
    0.28
    æĬķæĶ¾
    0.25
    endra
    0.25
    楼ä¸ĭ
    0.25
     site
    0.25
    جÙĬÙĦ
    0.25
    ederation
    0.24
    IBE
    0.24
    .synthetic
    0.24
    çıŃåŃIJ
    0.24
    Activations Density 0.013%

    No Known Activations