© 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. 99083
    Prev
    Next
    INDEX
    Explanations

    newly

    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
    åĨĻäºĨ
    -0.26
     assaulted
    -0.25
    æĹ¥åľ¨
    -0.25
    ût
    -0.24
    quia
    -0.24
    åıĹåĪ°å½±åĵį
    -0.24
     dzie
    -0.24
    fluence
    -0.23
     Shel
    -0.23
     ifdef
    -0.23
    POSITIVE LOGITS
     triple
    0.27
    __$
    0.26
    宥
    0.25
     grouped
    0.25
    ardless
    0.24
     fat
    0.24
    elles
    0.23
    beg
    0.23
     Wolf
    0.22
    åŁİå¸Ĥ群
    0.22
    Activations Density 0.017%

    No Known Activations