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. 53211
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    living
    -0.28
    é¢Ħéĺ²
    -0.27
    istan
    -0.25
    èij«èĬ¦
    -0.25
    mw
    -0.25
    åĩ»
    -0.25
    Multiplicity
    -0.24
    èIJ½å®ŀ
    -0.24
    å¹´é¾Ħ段
    -0.24
    Prime
    -0.24
    POSITIVE LOGITS
    ippers
    0.35
    ...]↵↵
    0.28
     tú
    0.27
    对ä¼ģä¸ļ
    0.26
     Monter
    0.25
     untouched
    0.24
    sar
    0.24
     meter
    0.24
    å¹´èµ·
    0.24
    cth
    0.24
    Activations Density 0.030%

    No Known Activations