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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40537
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļ份
    -0.27
    åĬ³åĬ¨
    -0.26
    ADC
    -0.26
    åĭŀ
    -0.26
    è¿Ļä¸Ģ天
    -0.26
    ä¸ī大
    -0.26
    çĻ¾
    -0.25
    èģĶåIJĪä¼ļ
    -0.25
    æĮĩ
    -0.24
    æłĩåĩĨåĮĸ
    -0.24
    POSITIVE LOGITS
     soph
    0.29
     Abr
    0.27
    opsy
    0.26
    伦
    0.26
    stops
    0.26
    nton
    0.25
    à¸Ļา
    0.25
    åĪºæ¿Ģ
    0.25
    æ¯ķç«Ł
    0.25
    æģŃ
    0.25
    Activations Density 0.035%

    No Known Activations