© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 162320
    Prev
    Next
    INDEX
    Explanations

    Informal, subjective writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»Ļä½łä»¬
    -0.28
    abis
    -0.28
    让大家
    -0.28
    bur
    -0.27
     equipments
    -0.25
    为大家
    -0.25
     ...↵↵↵↵
    -0.24
    Amb
    -0.24
     youths
    -0.24
    xEE
    -0.24
    POSITIVE LOGITS
    è·ŁæĪij
    0.46
    è·ŁæĪij说
    0.38
    对æĪij
    0.35
    åı«æĪij
    0.33
    享åıĹ
    0.30
    æİ¥åıĹ
    0.30
    äºĨè§£
    0.29
     менÑı
    0.29
    èİ·å¾Ĺ
    0.29
    é«Ķé©Ĺ
    0.28
    Activations Density 0.002%

    No Known Activations