© 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. 98574
    Prev
    Next
    INDEX
    Explanations

    "how much is too much"

    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
    erne
    -0.29
    åħī彩
    -0.28
    å¾Ģè¿Ķ
    -0.27
    æ½®
    -0.26
    culate
    -0.26
    åŃļ
    -0.26
    urons
    -0.25
     scand
    -0.25
    anke
    -0.25
     indebted
    -0.25
    POSITIVE LOGITS
     umbrella
    0.25
     categoryId
    0.25
    身ä½ĵåģ¥åº·
    0.25
    ifiable
    0.25
     ||
    0.25
    计è¾ĥ
    0.24
    ç»Ħéķ¿
    0.24
     lookout
    0.23
    å±ĭ
    0.23
    çĭ
    0.23
    Activations Density 0.005%

    No Known Activations