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. 146105
    Prev
    Next
    INDEX
    Explanations

    programming/computing

    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
    xdf
    -0.29
    ichel
    -0.29
    ignite
    -0.28
    çķĮéĻIJ
    -0.28
    请éĢīæĭ©
    -0.27
     infl
    -0.26
    æł·
    -0.26
    ptest
    -0.26
    éĢī
    -0.26
    æİĢ
    -0.25
    POSITIVE LOGITS
    mary
    0.32
    责任æĦŁ
    0.27
     neutral
    0.26
     harming
    0.26
    oS
    0.25
    yard
    0.25
    Ïį
    0.25
    æĻ¤
    0.25
    yards
    0.25
    (Property
    0.25
    Activations Density 0.004%

    No Known Activations