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. 146299
    Prev
    Next
    INDEX
    Explanations

    ate

    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
     nominee
    -0.26
    MENT
    -0.25
    çľģåĨħ
    -0.25
    \brief
    -0.24
    ãĥ¡ãĥ³ãĥĪ
    -0.24
    *x
    -0.24
    èģĶ社
    -0.24
    localized
    -0.23
    æĹ¥æ¶Īæģ¯
    -0.23
    è°ij
    -0.23
    POSITIVE LOGITS
    åĩºçĤī
    0.33
    .po
    0.26
    esi
    0.26
    xFFFFFF
    0.26
    shi
    0.26
    å¼ĭ
    0.25
    Ãłi
    0.25
    oshi
    0.24
     Uran
    0.24
    oS
    0.24
    Activations Density 0.004%

    No Known Activations