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. 47043
    Prev
    Next
    INDEX
    Explanations

    -ize/-ise suffixes

    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
    ions
    -0.28
     Ãľniversitesi
    -0.27
    è¿ĩ
    -0.26
    åĪĿ级
    -0.25
    çϾ
    -0.25
    ities
    -0.25
    imed
    -0.25
    ings
    -0.25
    ly
    -0.24
    fully
    -0.24
    POSITIVE LOGITS
    safe
    0.31
    rax
    0.28
    æľįåĬ¡å¹³åı°
    0.26
    инд
    0.26
    ä¸įæĺİ
    0.26
     punches
    0.25
    俵
    0.25
    dex
    0.25
    -fw
    0.25
    Ñīе
    0.25
    Activations Density 0.032%

    No Known Activations