© 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. 87134
    Prev
    Next
    INDEX
    Explanations

    Beginning, starting something

    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
    hält
    -0.35
    acci
    -0.28
    liest
    -0.27
    ahas
    -0.27
    /*@
    -0.27
    -vars
    -0.26
    ãģĿãģĨãģ§
    -0.26
    peats
    -0.25
     conviction
    -0.25
    æĬķèµĦé¢Ŀ
    -0.25
    POSITIVE LOGITS
    ->__
    0.32
     about
    0.25
     resulting
    0.25
     Trav
    0.24
    æ±ĩ
    0.24
    æĿ¥å®¾
    0.24
    导æ¼Ķ
    0.24
     background
    0.23
     GNU
    0.23
    æݨåĩº
    0.23
    Activations Density 0.012%

    No Known Activations