© 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. 99116
    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
    Negative Logits
     retrieved
    -0.26
    Bill
    -0.26
     GHC
    -0.26
    浪漫
    -0.26
    BorderStyle
    -0.26
     Forgot
    -0.25
     obtained
    -0.25
    bill
    -0.24
     donate
    -0.24
    èİ·åıĸ
    -0.24
    POSITIVE LOGITS
    å®ĥçļĦ
    0.29
    iction
    0.28
    åľ¨åħ¶
    0.28
    å®ĥ
    0.27
     quoi
    0.26
    ovel
    0.26
    IPS
    0.26
    âľİ
    0.25
    rix
    0.25
    åĪ°å¤Ħ
    0.25
    Activations Density 0.001%

    No Known Activations