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. 24565
    Prev
    Next
    INDEX
    Explanations

    variety of topics

    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
     Toro
    -0.26
    æĪij们ä¸Ģèµ·
    -0.25
    UGHT
    -0.25
    è¿ĩçļĦ
    -0.25
    rench
    -0.25
    轺
    -0.24
     amp
    -0.24
    _stdio
    -0.24
     american
    -0.24
    RIEND
    -0.24
    POSITIVE LOGITS
     Pros
    0.27
    beth
    0.27
    äºŃ
    0.27
    笤
    0.26
    ç¯
    0.25
    eny
    0.25
    anj
    0.25
    èĦĨ
    0.24
     stricter
    0.24
     buildings
    0.23
    Activations Density 0.785%

    No Known Activations