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. 146314
    Prev
    Next
    INDEX
    Explanations

    R

    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
    建æŀĦ
    -0.28
     till
    -0.27
    ooled
    -0.27
    -android
    -0.26
    idades
    -0.26
     Hyderabad
    -0.26
    åIJĥå¾Ĺ
    -0.25
    onso
    -0.24
    åį°åº¦
    -0.24
    á¹Ľ
    -0.24
    POSITIVE LOGITS
    Parts
    0.27
    edis
    0.27
     presentation
    0.26
    æµĥ
    0.25
    éªļ
    0.25
    馥
    0.25
    åĩıå¼±
    0.25
    æĻ®éĢļè¯Ŀ
    0.24
    交ä¼ļ
    0.24
    æ»Ł
    0.24
    Activations Density 0.280%

    No Known Activations