© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89120
    Prev
    Next
    INDEX
    Explanations

    code classes/models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģç»ı
    -0.28
    åij½è¿IJ
    -0.26
    -engine
    -0.26
    æİĮ
    -0.25
     Supern
    -0.25
     Starter
    -0.24
    ç«ĭãģ¡
    -0.24
     HOWEVER
    -0.24
    ìļ´
    -0.24
    å·¨
    -0.23
    POSITIVE LOGITS
    hart
    0.29
    nard
    0.28
    åĵģç±»
    0.28
    ifr
    0.26
    ilter
    0.25
    ioms
    0.24
    вин
    0.24
    неÑģ
    0.24
     Packing
    0.24
    çļĦä¾ĭåŃIJ
    0.24
    Activations Density 0.156%

    No Known Activations