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. 7-TRANSCODER-HP
    4. 24047
    Prev
    Next
    INDEX
    Explanations

    accidents/problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oola
    -0.31
     stal
    -0.28
     interpol
    -0.27
    ä¸įè§£
    -0.27
    cona
    -0.27
     //~
    -0.25
     ||=
    -0.25
    itä
    -0.24
     Cornwall
    -0.24
    _stderr
    -0.24
    POSITIVE LOGITS
    æĭĽ
    0.28
    èį¡
    0.28
    èĪŀ
    0.27
    )),
    0.26
    DebugEnabled
    0.25
    å¸
    0.25
    çī¹
    0.24
     "@/
    0.24
    ç½
    0.24
    æĮĩæķ°
    0.23
    Activations Density 0.001%

    No Known Activations