© 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. 23-TRANSCODER-HP
    7. 161669
    Prev
    Next
    INDEX
    Explanations

    Sensor/device data reading/transmission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪijäºĭ责任
    -0.30
    æ³ķå¾ĭ责任
    -0.28
     csr
    -0.27
    amat
    -0.26
     près
    -0.25
    oley
    -0.25
    ÑĥÑĪки
    -0.25
    expr
    -0.25
     Foley
    -0.25
    ling
    -0.24
    POSITIVE LOGITS
     automated
    0.34
     automatically
    0.33
    èĩªåĬ¨åĮĸ
    0.31
     automat
    0.30
     easy
    0.28
     automatic
    0.27
    tep
    0.27
    èĩªåĭķ
    0.27
     automát
    0.27
    _beta
    0.26
    Activations Density 0.006%

    No Known Activations