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. 27-TRANSCODER-HP
    4. 736
    Prev
    Next
    INDEX
    Explanations

    Online forum context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¯Ľ
    -0.39
     stomach
    -0.33
     hairs
    -0.33
    æ§½
    -0.31
     craw
    -0.29
    èĦĬ
    -0.28
    湿
    -0.28
     uneasy
    -0.27
     discomfort
    -0.26
    éĹ·
    -0.26
    POSITIVE LOGITS
    åIJ¸å¼ķ
    0.30
    åįļ
    0.27
    hop
    0.26
    æįŁä¼¤
    0.26
    é£İéĻ©
    0.26
    æĸ
    0.26
    å¸ĮæľĽèĥ½å¤Ł
    0.26
    伤害
    0.25
     Rape
    0.24
    åIJ¸å¼ķäºĨ
    0.24
    Activations Density 0.000%

    No Known Activations