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. 11-TRANSCODER-HP
    4. 53876
    Prev
    Next
    INDEX
    Explanations

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主ç¼ĸ
    -0.28
    è§£æĶ¾
    -0.27
    ent
    -0.26
    itation
    -0.26
    fusion
    -0.26
    æķ¬ä¸ļ
    -0.25
     Encyclopedia
    -0.25
    åĸij
    -0.25
    iting
    -0.25
    è·³è·ĥ
    -0.25
    POSITIVE LOGITS
    yw
    0.30
    ÑģÑĤвенно
    0.27
    ronics
    0.26
    isks
    0.25
    PLIC
    0.25
    ailand
    0.25
    озв
    0.25
    æľ«
    0.24
    bred
    0.24
     bargaining
    0.24
    Activations Density 0.219%

    No Known Activations