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. 21742
    Prev
    Next
    INDEX
    Explanations

    true

    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
     walkthrough
    -0.28
     hitch
    -0.27
    渣
    -0.26
     swe
    -0.25
    omain
    -0.25
    -cloud
    -0.25
     thermometer
    -0.25
    ä¸Ńä»ĭ
    -0.24
    åģı
    -0.24
    鸡汤
    -0.24
    POSITIVE LOGITS
    ilian
    0.28
    lü
    0.28
     SYMBOL
    0.27
    UX
    0.26
    yling
    0.26
     Species
    0.25
    äºĨä¸Ģæī¹
    0.25
    æĢĻ
    0.25
    å¼ĢåIJ¯
    0.24
    itung
    0.24
    Activations Density 0.004%

    No Known Activations