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. 24233
    Prev
    Next
    INDEX
    Explanations

    Old

    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
    ç¨ĭ度
    -0.28
    erate
    -0.27
    ender
    -0.26
    èĪªæµ·
    -0.26
    ens
    -0.26
    ittings
    -0.25
    ç©¿è¡£
    -0.24
    dire
    -0.24
    Degree
    -0.23
    uzzi
    -0.23
    POSITIVE LOGITS
    ActivityResult
    0.30
    obia
    0.27
    ä¸ĵä¸ļ人士
    0.25
    为æĤ¨æıIJä¾Ľ
    0.25
    .sim
    0.25
    èĽ®
    0.25
    ivist
    0.24
    chten
    0.24
    ...'
    0.24
     BaseActivity
    0.24
    Activations Density 0.002%

    No Known Activations