© 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. 131066
    Prev
    Next
    INDEX
    Explanations

    :

    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
    è¦ģéĹ»
    -0.27
    ensor
    -0.25
    好人
    -0.25
    곤
    -0.24
    侬
    -0.24
    inks
    -0.24
    ãĥIJãĥ©
    -0.23
    imus
    -0.23
     yours
    -0.23
    åıijçİ°éĹ®é¢ĺ
    -0.23
    POSITIVE LOGITS
     Credits
    0.26
    akan
    0.25
    bas
    0.24
    æĵħéķ¿
    0.24
    Bas
    0.24
    çĶŁåŃĺ
    0.24
    astered
    0.23
     Indonesian
    0.23
    utt
    0.23
    KV
    0.23
    Activations Density 0.005%

    No Known Activations