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. 15401
    Prev
    Next
    INDEX
    Explanations

    Malaria and scientific research

    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
    itate
    -0.27
    inished
    -0.26
    รา
    -0.25
    shed
    -0.25
    ç³ĸ
    -0.24
     Trev
    -0.24
    åĽ¢
    -0.24
     Stats
    -0.23
    æĪı
    -0.23
    emo
    -0.23
    POSITIVE LOGITS
     mant
    0.27
    soever
    0.27
    Pointer
    0.26
     Mant
    0.26
    éĩįå·¥
    0.26
    _bel
    0.25
    udit
    0.25
    _pf
    0.25
    æĬ«
    0.24
    places
    0.24
    Activations Density 0.002%

    No Known Activations