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. 146559
    Prev
    Next
    INDEX
    Explanations

    er

    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
     instrumental
    -0.29
    ioni
    -0.28
    olis
    -0.28
    .sent
    -0.27
    -invalid
    -0.27
    inton
    -0.27
    .defaultValue
    -0.26
    äsent
    -0.26
    éī´å®ļ
    -0.25
    .sdk
    -0.24
    POSITIVE LOGITS
    çµ±
    0.31
    绣
    0.27
    enic
    0.26
     lle
    0.26
    oline
    0.25
    æĤ»
    0.25
     Lester
    0.25
    绣ä¸Ģ
    0.25
    æī«é»ij
    0.24
     Products
    0.24
    Activations Density 0.005%

    No Known Activations