© 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. 14-TRANSCODER-HP
    7. 40229
    Prev
    Next
    INDEX
    Explanations

    pragmatic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jej
    -0.28
    éĺħ读åħ¨æĸĩ
    -0.27
    ç»ħ
    -0.27
    åĪİ
    -0.25
    semi
    -0.25
    ="")↵
    -0.24
    |h
    -0.24
    åľ»
    -0.24
    严谨
    -0.24
    igne
    -0.24
    POSITIVE LOGITS
    太æŀģ
    0.27
    ãĤ¤ãĥ³ãĤ¿
    0.27
     fitted
    0.26
    çIJĨäºĭä¼ļ
    0.25
    è´¬
    0.24
    eva
    0.24
    ä¸ģ
    0.24
     counsel
    0.24
    stock
    0.24
     weaker
    0.24
    Activations Density 0.113%

    No Known Activations