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. 97947
    Prev
    Next
    INDEX
    Explanations

    system

    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
    çݳ
    -0.29
    æĢ»æķ°
    -0.26
     polar
    -0.26
     Studies
    -0.26
    gree
    -0.25
    isible
    -0.25
    nowrap
    -0.24
    çģĮ
    -0.24
     Isles
    -0.24
     surpass
    -0.23
    POSITIVE LOGITS
    eci
    0.31
    ycling
    0.30
    uess
    0.27
    ebra
    0.26
    çݯä¿Ŀ
    0.26
    ecz
    0.26
    ee
    0.25
    oo
    0.25
     Dup
    0.24
    eko
    0.24
    Activations Density 0.002%

    No Known Activations