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. 73092
    Prev
    Next
    INDEX
    Explanations

    Relationships and feelings

    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
     cycl
    -0.25
    ä¿¡
    -0.24
     att
    -0.24
    çͲ
    -0.24
     Cycl
    -0.24
    ç¼İ
    -0.24
     Guide
    -0.24
    å¥ij
    -0.24
    顺
    -0.24
    bor
    -0.23
    POSITIVE LOGITS
    ios
    0.26
    车éģĵ
    0.26
    ermen
    0.26
    åīįåı°
    0.25
    ım
    0.25
    ç°ı
    0.25
    ilan
    0.24
     glEnd
    0.24
    çļĦ女åĦ¿
    0.24
    >Title
    0.24
    Activations Density 0.011%

    No Known Activations