© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 181
    Prev
    Next
    INDEX
    Explanations

    mixed, wide range of topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éŁ³
    -0.27
    ä»ŀ
    -0.26
    permalink
    -0.26
    æıIJ
    -0.26
    çļĦå£°éŁ³
    -0.26
    å¾Ĺåĩº
    -0.26
    æłĵ
    -0.26
    à¸ļาย
    -0.26
    grass
    -0.25
    çīµ
    -0.25
    POSITIVE LOGITS
    Pager
    0.26
    RLF
    0.25
     isLoading
    0.25
    irit
    0.24
    åİĨåı²æĸ°
    0.24
     Aç
    0.23
    irst
    0.23
    !--
    0.23
    ÑĤеÑĢ
    0.23
    _HANDLE
    0.23
    Activations Density 0.011%

    No Known Activations