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. 53841
    Prev
    Next
    INDEX
    Explanations

    No obvious pattern found.AM

    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
    çļĦä¸ľè¥¿
    -0.25
    atat
    -0.24
    èµĦäº§è´ŁåĢº
    -0.24
    缱
    -0.24
     sworn
    -0.24
    flip
    -0.24
    åĢ¡
    -0.24
    çļĦä¿¡æģ¯
    -0.24
    Protocol
    -0.24
    pirit
    -0.24
    POSITIVE LOGITS
    rä
    0.28
     Redistributions
    0.27
    bow
    0.25
    LOT
    0.24
     climb
    0.24
     '|'
    0.24
    LICENSE
    0.23
    åīįæıIJ
    0.23
    åĪĨæķ£
    0.23
    ware
    0.23
    Activations Density 0.077%

    No Known Activations