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. 24119
    Prev
    Next
    INDEX
    Explanations

    significant

    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
     booth
    -0.26
    :date
    -0.25
     Quadr
    -0.25
     inbound
    -0.25
    ings
    -0.24
    éķ¿éķ¿
    -0.24
     "=",
    -0.24
    hait
    -0.24
    ÎĹ
    -0.23
    ή
    -0.23
    POSITIVE LOGITS
    AEA
    0.28
    èĬ±çĵ£
    0.26
    鼬
    0.25
    айл
    0.25
    åīĶ
    0.24
    ä½İ头
    0.24
    åij·
    0.24
    伪
    0.24
    读
    0.24
    yte
    0.24
    Activations Density 0.002%

    No Known Activations