© 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. 111007
    Prev
    Next
    INDEX
    Explanations

    Abilities/Actions/Verbs

    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
    ApiOperation
    -0.25
    amp
    -0.24
    rock
    -0.23
    ä¸Ģ页
    -0.23
    ä½ij
    -0.23
    AMP
    -0.23
    éĴİ
    -0.23
    av
    -0.23
     getPage
    -0.23
    strength
    -0.22
    POSITIVE LOGITS
    anship
    0.27
    æŶéĹ´ä¸º
    0.27
    æĦı大
    0.26
    æīįç®Ĺ
    0.25
    ohana
    0.24
    ionate
    0.24
     simul
    0.24
     "...
    0.24
    认è¯Ĩ
    0.24
     fewer
    0.23
    Activations Density 0.014%

    No Known Activations