Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 7-TRANSCODER-HP
    4. 24682
    Prev
    Next
    INDEX
    Explanations

    uch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arez
    -0.28
    ä¸Ģå°ģ
    -0.26
    è¾¹ä¸Ĭ
    -0.25
     clo
    -0.25
    cp
    -0.25
    TURE
    -0.25
     voice
    -0.24
    _residual
    -0.24
     verdienen
    -0.24
    äºij端
    -0.24
    POSITIVE LOGITS
    [hash
    0.28
    builders
    0.27
    Ñĥни
    0.26
    纥
    0.26
    hash
    0.26
    åĨ²åĩ»
    0.25
    æł¹æį®ä¸įåIJĮ
    0.25
     NAMES
    0.25
    æĴ¼
    0.24
    pir
    0.24
    Activations Density 0.782%

    No Known Activations