© 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. 111140
    Prev
    Next
    INDEX
    Explanations

    by

    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
    ç§Ģ丽
    -0.30
    äºİæѤ
    -0.26
    ario
    -0.25
     route
    -0.25
    secure
    -0.25
    å°Ĩæĺ¯
    -0.25
    elines
    -0.24
    arios
    -0.24
    æį®æѤ
    -0.24
    æķĻèĤ²æķĻåѦ
    -0.24
    POSITIVE LOGITS
     Narr
    0.27
    utters
    0.26
    ('.')[
    0.26
    otropic
    0.26
     Patrol
    0.26
     sod
    0.25
    æijĺ
    0.25
    åĬŁå¤«
    0.24
     Nunes
    0.24
     Pat
    0.24
    Activations Density 0.007%

    No Known Activations