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. 23-TRANSCODER-HP
    4. 14771
    Prev
    Next
    INDEX
    Explanations

    defense against something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģåī¯
    -0.27
    éϤäºĨ
    -0.26
    两款
    -0.25
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.25
    端
    -0.24
    Barrier
    -0.24
    ervative
    -0.24
    itted
    -0.24
    èϽçĦ¶æĺ¯
    -0.23
    -contained
    -0.23
    POSITIVE LOGITS
     enemies
    0.31
    å¤ĸçķĮ
    0.29
    roads
    0.28
    çļĦçľ¼çĿĽ
    0.27
    èĩªçĦ¶çģ¾å®³
    0.27
     hostile
    0.27
    æķĮ人
    0.26
     storms
    0.26
     hitters
    0.26
    éĩį大
    0.25
    Activations Density 0.002%

    No Known Activations