© 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. 282
    Prev
    Next
    INDEX
    Explanations

    oro

    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
    ÑĢод
    -0.28
    ngr
    -0.28
    å±Ģ
    -0.27
    ucas
    -0.26
    nets
    -0.26
    èĤ©
    -0.26
    ä¸Ģ件
    -0.25
    oppers
    -0.25
    ãģį
    -0.25
    anja
    -0.24
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.29
     purs
    0.25
    commended
    0.25
    追赶
    0.25
     einf
    0.25
    ä¸ŃåĽ½ä¼ģä¸ļ
    0.24
    èİĻ
    0.24
    åĩłå®¶
    0.24
    åģľçķĻåľ¨
    0.24
     ì¶Ķ
    0.24
    Activations Density 0.029%

    No Known Activations