© 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. 99004
    Prev
    Next
    INDEX
    Explanations

    referral

    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
     truths
    -0.27
    enor
    -0.25
    å¿į
    -0.25
    terminal
    -0.25
     terminal
    -0.24
    æĢİä¹Īçľĭ
    -0.24
    corr
    -0.23
    yor
    -0.23
     terminals
    -0.23
    correct
    -0.22
    POSITIVE LOGITS
    éĢļçŁ¥
    0.29
     notifying
    0.27
     nicely
    0.26
    /contact
    0.26
    è´Ī
    0.24
     notify
    0.24
    YPE
    0.24
    çļĦæĹ¥
    0.24
    æĹ¥æŃ£å¼ı
    0.24
     nice
    0.23
    Activations Density 0.022%

    No Known Activations