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. 53793
    Prev
    Next
    INDEX
    Explanations

    deception

    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
    PerPage
    -0.31
    estate
    -0.27
    éļį
    -0.26
    诱人
    -0.26
    以为
    -0.26
    afs
    -0.26
     fooled
    -0.26
    à¹ģà¸Ĺ
    -0.26
    reveal
    -0.26
    WG
    -0.25
    POSITIVE LOGITS
    åİŁå§ĭ
    0.27
    ovement
    0.27
    thumbs
    0.27
    æĺ¯ä¸ŃåĽ½
    0.27
    èºį
    0.26
    uma
    0.26
    clin
    0.26
    æĺ¯æĪijåĽ½
    0.25
    iful
    0.25
    éĿŀ常好
    0.25
    Activations Density 0.012%

    No Known Activations