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. 11-TRANSCODER-HP
    4. 46440
    Prev
    Next
    INDEX
    Explanations

    loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    妹
    -0.30
     öd
    -0.27
    itary
    -0.26
    usual
    -0.26
    涨
    -0.26
    æŃĨ
    -0.25
     гл
    -0.25
    emer
    -0.25
    ä¼¼
    -0.25
    å½»
    -0.25
    POSITIVE LOGITS
    å¥Ħ
    0.28
    人äºĭ
    0.26
    ennon
    0.26
    sandbox
    0.25
    cq
    0.24
    Teams
    0.24
    åĽ¢éĺŁ
    0.24
     MCS
    0.24
    /Object
    0.24
    /accounts
    0.24
    Activations Density 1.177%

    No Known Activations