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. 50
    Prev
    Next
    INDEX
    Explanations

    life

    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
    füg
    -0.30
    _attached
    -0.27
     empirical
    -0.27
    oley
    -0.26
     competit
    -0.26
    ongsTo
    -0.25
    ä½ľå¼Ĭ
    -0.25
    诱
    -0.25
    åģ¶
    -0.25
     advertise
    -0.24
    POSITIVE LOGITS
    .unwrap
    0.26
    Gap
    0.26
     WebClient
    0.26
    ib
    0.26
    ife
    0.25
     trụ
    0.25
    Parms
    0.25
    ika
    0.25
    Props
    0.24
     fe
    0.24
    Activations Density 0.002%

    No Known Activations