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. 146313
    Prev
    Next
    INDEX
    Explanations

    Denaturation or denervation

    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
    åĪĨ级
    -0.27
    æľīçļĦ人
    -0.25
    unner
    -0.25
    linger
    -0.25
    æ½®
    -0.25
     discord
    -0.25
    ouro
    -0.24
     ak
    -0.24
    acf
    -0.24
    ONGL
    -0.24
    POSITIVE LOGITS
     Mondays
    0.29
    ç¼ļ
    0.26
    pping
    0.25
    éĺķ
    0.25
    drops
    0.25
     phạm
    0.25
     Fridays
    0.25
    sumer
    0.24
    èĽ±
    0.24
     distract
    0.24
    Activations Density 0.029%

    No Known Activations