© 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. 129135
    Prev
    Next
    INDEX
    Explanations

    Public licensing

    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
     checker
    -0.26
     viz
    -0.26
    amente
    -0.25
    ouis
    -0.25
     —↵↵
    -0.24
    onga
    -0.24
    ï¼ļ"
    -0.24
    rocess
    -0.23
    avan
    -0.23
    eous
    -0.23
    POSITIVE LOGITS
    æįİ
    0.26
    æĭ¼éŁ³
    0.25
    è¾ħ
    0.25
    powers
    0.25
     powers
    0.24
    sup
    0.24
    asn
    0.23
    Accent
    0.23
    éĢļçĶ¨
    0.23
    åĬłçıŃ
    0.23
    Activations Density 0.004%

    No Known Activations