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. 16
    Prev
    Next
    INDEX
    Explanations

    up

    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
    eks
    -0.30
    ôi
    -0.29
    çĥ§
    -0.28
    oogle
    -0.28
    oft
    -0.27
    shan
    -0.26
    atories
    -0.25
     Paran
    -0.24
    ashboard
    -0.24
    ollow
    -0.24
    POSITIVE LOGITS
    pch
    0.26
     Compensation
    0.25
    _since
    0.25
     distinction
    0.24
    çĿĢ
    0.24
     Dot
    0.23
    Coroutine
    0.23
     dismissal
    0.23
    æ¯ĽçĹħ
    0.23
    å®īå¨ľ
    0.23
    Activations Density 0.005%

    No Known Activations