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. 46777
    Prev
    Next
    INDEX
    Explanations

    aw

    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
    ündig
    -0.32
    apo
    -0.26
     presente
    -0.26
    åıĤåĬł
    -0.25
    atat
    -0.25
    éĽĨæĪIJ
    -0.25
    ernen
    -0.25
    ilon
    -0.25
    peon
    -0.25
    prend
    -0.24
    POSITIVE LOGITS
    éĤ£äºº
    0.28
    è¿Ļ项
    0.27
    Unnamed
    0.26
    JKLM
    0.26
    æīįåı¯ä»¥
    0.26
    æīįæĺ¯çľŁæŃ£
    0.25
     Him
    0.25
    soft
    0.24
     demi
    0.24
    çĦ¦æĢ¥
    0.24
    Activations Density 3.940%

    No Known Activations