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. 7-TRANSCODER-HP
    4. 184
    Prev
    Next
    INDEX
    Explanations

    health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;m
    -0.29
    uti
    -0.27
    ÃŃculo
    -0.26
    åī¡
    -0.26
    	ST
    -0.26
    èµ·
    -0.26
    åľº
    -0.26
    ice
    -0.25
     m
    -0.25
    Progress
    -0.25
    POSITIVE LOGITS
    æĭīæĸ¯
    0.29
    _stdout
    0.28
    çݩ游æĪı
    0.27
     todd
    0.27
    æ©ŁéĹľ
    0.26
     Opport
    0.25
     widest
    0.24
    ocols
    0.24
     efficiencies
    0.24
    zew
    0.24
    Activations Density 0.001%

    No Known Activations