© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 99265
    Prev
    Next
    INDEX
    Explanations

    day

    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
    Negative Logits
    -thread
    -0.31
    ewire
    -0.31
    èļĵ
    -0.25
    æĸ°çļĦä¸Ģå¹´
    -0.25
    祸
    -0.25
    åĬ¨æľº
    -0.24
    说æĪij
    -0.24
    Ỽi
    -0.24
    iterated
    -0.24
    endpoint
    -0.24
    POSITIVE LOGITS
    (s
    0.30
    éħ®
    0.29
     possible
    0.28
     ago
    0.26
    bing
    0.26
    functions
    0.25
    TypeDef
    0.24
     make
    0.24
    Function
    0.24
    less
    0.24
    Activations Density 0.022%

    No Known Activations