© 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. 27-TRANSCODER-HP
    7. 7747
    Prev
    Next
    INDEX
    Explanations

    buildings and news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    kus
    -0.27
    ç½Ķ
    -0.27
    ä¸Ģ段æŶéĹ´
    -0.26
     instrument
    -0.26
    æĺ¾
    -0.25
    itemap
    -0.24
    仪
    -0.24
    -loader
    -0.23
    è¿ĩçļĦ
    -0.23
    -ranging
    -0.23
    POSITIVE LOGITS
    éĢģåİ»
    0.29
     sustainability
    0.29
     Sustainability
    0.26
    ÑĤики
    0.26
    ablo
    0.26
     Criteria
    0.25
     communion
    0.25
     appeal
    0.24
    åħ±é¸£
    0.23
    usband
    0.23
    Activations Density 0.002%

    No Known Activations