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. 146268
    Prev
    Next
    INDEX
    Explanations

    McCormack

    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
     heir
    -0.29
    mapping
    -0.28
    (mapping
    -0.27
     mappings
    -0.27
    appy
    -0.27
    mour
    -0.27
    ç»ı纪
    -0.26
     Strikes
    -0.26
    aps
    -0.24
    APS
    -0.24
    POSITIVE LOGITS
    estion
    0.28
    ìĽIJ
    0.27
    asin
    0.27
    迦
    0.26
    æĬĺ
    0.26
    æĹģ
    0.26
    次
    0.26
     Gle
    0.26
    æĭ¼éٳ
    0.25
    bulan
    0.25
    Activations Density 0.004%

    No Known Activations