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. 1506
    Prev
    Next
    INDEX
    Explanations

    fever, medical issues

    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
    æĹ¬
    -0.28
    å¤Ħåľ¨
    -0.27
     mechanic
    -0.27
    eing
    -0.26
     clue
    -0.26
    åıĺ
    -0.26
     Ethan
    -0.25
    缩水
    -0.25
    age
    -0.25
    æĹ¶ä»£çļĦ
    -0.24
    POSITIVE LOGITS
    unic
    0.30
    é̵
    0.26
    adol
    0.26
    iqu
    0.26
    _PHYS
    0.25
    TPL
    0.24
    (nt
    0.24
    -alist
    0.24
    ny
    0.23
    лом
    0.23
    Activations Density 0.001%

    No Known Activations