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. 9
    Prev
    Next
    INDEX
    Explanations

    UNICATION

    np_max-act · gemini-2.0-flash

    mentions of the Federal Communications Commission and similar proper-noun references to communications agencies and regulators.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
    ancode
    -0.29
    assage
    -0.28
     spyOn
    -0.28
    Vent
    -0.26
    isas
    -0.25
     Graphics
    -0.24
    èİ·å¾ĹæĦŁ
    -0.24
    //{{
    -0.24
     nors
    -0.24
    asso
    -0.24
    POSITIVE LOGITS
     shades
    0.27
     attention
    0.26
    æĦŁçŁ¥
    0.26
    preter
    0.25
    顽
    0.25
     Ryder
    0.25
    Attention
    0.25
     Attention
    0.24
    ä½ıéĻ¢
    0.24
     Signal
    0.24
    Activations Density 0.001%

    No Known Activations