© 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. 89239
    Prev
    Next
    INDEX
    Explanations

    Background/Explanatory text

    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
    没å¿ħè¦ģ
    -0.31
    culate
    -0.28
    lename
    -0.28
     STDERR
    -0.26
     mistaken
    -0.26
    Ø´Ùĩ
    -0.26
     wasted
    -0.25
     incorrect
    -0.24
     correct
    -0.24
    çļĦé«ĺ度
    -0.24
    POSITIVE LOGITS
    iam
    0.28
     Constructors
    0.27
    ç°ª
    0.26
    portal
    0.25
    iy
    0.25
    æĺŁ
    0.25
    ulares
    0.24
    个çĻ¾åĪĨ
    0.24
     ZEND
    0.24
    çİĩ为
    0.24
    Activations Density 9.868%

    No Known Activations