© 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. 19-TRANSCODER-HP
    7. 6109
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    误导
    -0.27
    å¹»
    -0.25
    ril
    -0.25
    å®ĺ
    -0.24
    manent
    -0.24
    æĥ¯
    -0.24
    -indent
    -0.24
    Îĵ
    -0.23
     preferably
    -0.23
    haps
    -0.23
    POSITIVE LOGITS
    æīĵæĭĽåij¼
    0.26
    ä½Ķ
    0.24
    å·¥ç¨ĭå¸Ī
    0.24
    è¿Ļ个è¯į
    0.24
    _INST
    0.23
    |#
    0.23
    ’T
    0.23
    |--
    0.23
    mom
    0.23
    gesch
    0.23
    Activations Density 0.022%

    No Known Activations