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. 97982
    Prev
    Next
    INDEX
    Explanations

    free

    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
    earer
    -0.28
    æĬ¬å¤´
    -0.27
     Lager
    -0.26
     kê
    -0.25
    decl
    -0.25
    èĻı
    -0.25
    _pagination
    -0.24
    亲çαçļĦ
    -0.24
    èIJ½åľ°
    -0.24
    ographics
    -0.24
    POSITIVE LOGITS
     encompass
    0.29
    ennent
    0.28
    æĶ¶
    0.27
    icip
    0.25
    ummer
    0.25
     encompasses
    0.25
     geg
    0.24
    жен
    0.24
    ance
    0.24
    åĮħ
    0.24
    Activations Density 0.029%

    No Known Activations