© 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. 12-TRANSCODER-HP
    7. 23583
    Prev
    Next
    INDEX
    Explanations

    inda

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relat
    -0.28
     practiced
    -0.27
    åIJ¦
    -0.25
    碼
    -0.24
    +</
    -0.24
    atham
    -0.24
    è¯Ģ
    -0.24
     Watkins
    -0.24
    èģĶç½ij
    -0.24
    allel
    -0.23
    POSITIVE LOGITS
    eper
    0.31
    æ±ģ
    0.29
    Argb
    0.29
    uzzi
    0.27
    :min
    0.25
    -AA
    0.25
    å¼ĢæºIJ
    0.25
    ourke
    0.24
    hr
    0.24
    æĬĢæľ¯åĴĮ
    0.24
    Activations Density 0.000%

    No Known Activations