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. 67354
    Prev
    Next
    INDEX
    Explanations

    the

    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
    å±ħ
    -0.28
     illegally
    -0.25
    å¾ĺå¾Ĭ
    -0.25
    ä»įåľ¨
    -0.25
    çΰ
    -0.25
    ipline
    -0.24
    åĨ·åĨ·
    -0.24
     Laf
    -0.24
    æ·¡åĮĸ
    -0.24
    acula
    -0.24
    POSITIVE LOGITS
    ato
    0.29
    atos
    0.27
     rounds
    0.26
    /ros
    0.26
    eden
    0.25
    ä½Ĩ她
    0.24
    Secondary
    0.24
    èݲèĬ±
    0.24
    .RegisterType
    0.24
    alez
    0.23
    Activations Density 0.005%

    No Known Activations