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. 2-TRANSCODER-HP
    4. 145
    Prev
    Next
    INDEX
    Explanations

    mineral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_2.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.2.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lder
    -0.28
    asma
    -0.28
    tparam
    -0.27
    åį¢
    -0.26
    maal
    -0.26
    asive
    -0.26
    asting
    -0.26
    第äºĮ天
    -0.25
    asley
    -0.25
     Rig
    -0.24
    POSITIVE LOGITS
    æł·åŃIJ
    0.28
     mine
    0.27
    ä¸į妨
    0.26
     util
    0.25
    edBy
    0.25
     mined
    0.25
     minib
    0.24
     Miner
    0.24
    ite
    0.24
    ä¸įå¦Ĥ
    0.24
    Activations Density 14.449%

    No Known Activations