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. 24141
    Prev
    Next
    INDEX
    Explanations

    web content

    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
    ä¿®åħ»
    -0.28
    raq
    -0.28
     заг
    -0.27
     translate
    -0.27
    år
    -0.26
    èµĽ
    -0.26
    isans
    -0.25
    éĥ¨åī¯
    -0.25
     posed
    -0.25
    éĻ¢éĻ¢éķ¿
    -0.24
    POSITIVE LOGITS
    edb
    0.26
    åĽŀæļĸ
    0.26
    ầu
    0.25
    inium
    0.25
    iales
    0.24
    rouch
    0.24
    bdd
    0.24
     pData
    0.24
    åħ¬çĽĬ
    0.24
     Laptop
    0.24
    Activations Density 0.005%

    No Known Activations