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. 3862
    Prev
    Next
    INDEX
    Explanations

    over

    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
     ENG
    -0.26
     Inst
    -0.26
     rigs
    -0.24
    roc
    -0.24
    .Byte
    -0.24
    å¿Į
    -0.24
    èµĦæĸĻ
    -0.24
     Taiwanese
    -0.23
    åĪļ
    -0.23
    gee
    -0.23
    POSITIVE LOGITS
    ä¼łæĴŃ
    0.28
     sina
    0.26
    å°ijæķ°
    0.26
     minorities
    0.26
    ä¼łå¯¼
    0.26
    Permanent
    0.26
    å¾Ĥ
    0.25
    iously
    0.25
    åĽ¢
    0.24
    çŃ·
    0.24
    Activations Density 0.812%

    No Known Activations