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. 53585
    Prev
    Next
    INDEX
    Explanations

    angles and perpendicularity

    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
    _BANK
    -0.26
    icus
    -0.26
    -HT
    -0.25
     communist
    -0.24
    icum
    -0.24
     Ferry
    -0.24
    theros
    -0.23
     thân
    -0.23
     hypoc
    -0.23
    meric
    -0.23
    POSITIVE LOGITS
    æĿ¥èĩª
    0.30
    elig
    0.27
    æ±ĩ
    0.26
    éĹªç͵
    0.26
    åĿĩ为
    0.26
     Nex
    0.26
    âģ
    0.25
    æijĺè¦ģ
    0.25
    å·¥
    0.25
    æķ·
    0.25
    Activations Density 0.016%

    No Known Activations