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. 67370
    Prev
    Next
    INDEX
    Explanations

    protecting something

    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
    以为
    -0.29
    Gender
    -0.28
    .sex
    -0.27
    _gender
    -0.26
    æĢ§åĪ«
    -0.26
     sample
    -0.25
    .gender
    -0.25
    gender
    -0.25
    ãĥıãĤ¦ãĤ¹
    -0.25
    ufe
    -0.25
    POSITIVE LOGITS
    ä¸ªå·¥ä½ľæĹ¥
    0.28
    à¤Ķ
    0.27
    没æľīå¿ħè¦ģ
    0.27
     Polic
    0.25
    è¡°éĢĢ
    0.25
    åIJĮå¿Ĺ
    0.25
     freedoms
    0.24
    cd
    0.24
     exiting
    0.24
    getc
    0.24
    Activations Density 0.005%

    No Known Activations