© 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. 113076
    Prev
    Next
    INDEX
    Explanations

    General information/reports

    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
    -tracking
    -0.25
     gospel
    -0.24
    keletal
    -0.23
    Odd
    -0.23
    YLE
    -0.23
    ãĤ·ãĥ§ãĥ³
    -0.23
    PerPage
    -0.23
    aussian
    -0.23
     Vend
    -0.23
    (Mouse
    -0.22
    POSITIVE LOGITS
     metre
    0.28
    kowski
    0.26
     internal
    0.25
     forks
    0.25
    MP
    0.24
    onne
    0.24
    ãĥ¥ãĥ¼
    0.23
    åį®
    0.23
    lude
    0.23
     standby
    0.23
    Activations Density 0.074%

    No Known Activations