© 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. 197
    Prev
    Next
    INDEX
    Explanations

    plants

    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
    nda
    -0.28
     turno
    -0.27
    xec
    -0.26
    ä¸ĩè¾Ĩ
    -0.26
     categoria
    -0.25
    osl
    -0.25
     damned
    -0.25
    ypy
    -0.25
    ube
    -0.24
    åIJİåĨį
    -0.24
    POSITIVE LOGITS
    丰å¯Į
    0.27
    çŃĸ
    0.26
     Flash
    0.26
    çļĦè§Ĵèī²
    0.26
     richer
    0.25
     flash
    0.25
     van
    0.25
    ç©·
    0.24
    身ä¸Ĭ
    0.24
     DEC
    0.24
    Activations Density 4.085%

    No Known Activations