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. 54576
    Prev
    Next
    INDEX
    Explanations

    Academy

    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
    reff
    -0.26
    èĸĦå¼±
    -0.24
    aran
    -0.24
    isson
    -0.24
    Closing
    -0.24
     closing
    -0.24
    arkan
    -0.24
    è¡Ĺä¸Ĭ
    -0.24
     perish
    -0.24
    éĺ¿æł¹
    -0.23
    POSITIVE LOGITS
    é̾
    0.31
    8
    0.28
    æķ´å½¢
    0.27
    ove
    0.27
    å¾ģ
    0.26
    bases
    0.26
    ç¡®
    0.26
    ise
    0.26
    Jose
    0.26
    绣
    0.26
    Activations Density 0.011%

    No Known Activations