© 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. 88153
    Prev
    Next
    INDEX
    Explanations

    that

    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
     ad
    -0.28
    ä¸ĭéĿ¢
    -0.27
    çĶ¨æĪ·
    -0.26
    ĪæĿĥ
    -0.26
    able
    -0.25
     dav
    -0.25
    åľ¨åIJĮä¸Ģ
    -0.25
    è¿Ļæł·çļĦè¯Ŀ
    -0.25
    åĩºæīĭ
    -0.25
    AGO
    -0.24
    POSITIVE LOGITS
    åħ¶ä¸ŃåĮħæĭ¬
    0.30
    splice
    0.28
    stdafx
    0.27
    typeorm
    0.27
    xee
    0.26
    asia
    0.24
    *sp
    0.24
     meal
    0.24
     prem
    0.24
    enza
    0.24
    Activations Density 0.024%

    No Known Activations