© 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. 9663
    Prev
    Next
    INDEX
    Explanations

    part

    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
     onboard
    -0.27
    irse
    -0.25
     installs
    -0.25
    èĮĦ
    -0.24
     idi
    -0.24
     subscription
    -0.24
    æĬ¥è®°èĢħ
    -0.24
    çĥĿ
    -0.24
    æĪijä»¬çŁ¥éģĵ
    -0.24
    è±ģ
    -0.24
    POSITIVE LOGITS
    aim
    0.27
    scheme
    0.27
    ä¸įåĪ©
    0.26
     inverted
    0.24
    é«ĺãģı
    0.24
    _dom
    0.24
    çĹĴ
    0.24
    gesch
    0.24
    MAKE
    0.24
    åĢĴ
    0.24
    Activations Density 0.009%

    No Known Activations