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. 227
    Prev
    Next
    INDEX
    Explanations

    are

    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
    å¤ļä¹Ī
    -0.27
    ç±³å°Ķ
    -0.26
    nip
    -0.25
     Sidney
    -0.25
    abh
    -0.25
    olio
    -0.24
    method
    -0.24
    mouth
    -0.24
    缩å°ı
    -0.24
    ador
    -0.24
    POSITIVE LOGITS
     contact
    0.29
     Kontakt
    0.28
     Contacts
    0.28
     contacts
    0.27
    毡
    0.26
    级以ä¸Ĭ
    0.25
    &T
    0.24
     BOTH
    0.24
    çݰå®ŀ
    0.24
     yat
    0.24
    Activations Density 0.003%

    No Known Activations