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. 11-TRANSCODER-HP
    4. 46740
    Prev
    Next
    INDEX
    Explanations

    atory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪIJç«ĭ以æĿ¥
    -0.32
    åĴ¥
    -0.30
    å±ķä½į
    -0.30
    çī½
    -0.28
    /Object
    -0.26
    :length
    -0.26
    åĿļå®ŀçļĦ
    -0.26
    å¥Ķ
    -0.25
    KE
    -0.25
    /functions
    -0.25
    POSITIVE LOGITS
    éļĶ
    0.28
    çĻ»
    0.27
    åľ¹
    0.26
     microscopy
    0.25
    .gov
    0.24
    ase
    0.24
    arness
    0.24
    äu
    0.24
    -Day
    0.24
    arning
    0.24
    Activations Density 0.640%

    No Known Activations