© 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. 9-TRANSCODER-HP
    7. 29447
    Prev
    Next
    INDEX
    Explanations

    mac

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dise
    -0.26
    ç²Ĺ
    -0.25
     correl
    -0.24
     nig
    -0.24
    çŁŃçŁŃ
    -0.24
     pag
    -0.23
    arten
    -0.23
    æĹ©çĤ¹
    -0.23
     evolution
    -0.23
    èĽĦ
    -0.23
    POSITIVE LOGITS
    shiv
    0.27
    è¾IJ
    0.24
    è´¸æĺĵ
    0.24
     ThÆ°Æ¡ng
    0.24
    anship
    0.24
    flu
    0.23
     dens
    0.23
    -trade
    0.23
    quarter
    0.23
    ogram
    0.23
    Activations Density 0.515%

    No Known Activations