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. 146305
    Prev
    Next
    INDEX
    Explanations

    Environment

    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
    bell
    -0.27
    ä¼Ľ
    -0.26
    驹
    -0.26
    ØŃÙģ
    -0.26
    ,No
    -0.25
    nev
    -0.25
    æľīä»»ä½ķ
    -0.25
    /Library
    -0.25
     Pty
    -0.24
     informative
    -0.24
    POSITIVE LOGITS
    à¹Ģà¸ķ
    0.29
     deepest
    0.27
    htt
    0.27
    æ³ķ
    0.26
    è¿ľæĸ¹
    0.25
    åķĨ
    0.24
    preneur
    0.24
    è¦ģç´§
    0.24
    .tem
    0.24
    contest
    0.24
    Activations Density 0.033%

    No Known Activations