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. 54575
    Prev
    Next
    INDEX
    Explanations

    age

    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
    就被
    -0.27
     scor
    -0.27
    éĶ·
    -0.25
    æ¿Ģç´ł
    -0.25
    é¢Ħç®Ĺ
    -0.24
    åģı
    -0.24
    LECTION
    -0.23
    ALE
    -0.23
    è¯ĬçĸĹ
    -0.23
     hö
    -0.23
    POSITIVE LOGITS
    osi
    0.30
     Location
    0.27
     Initialization
    0.26
    èѦåijĬ
    0.26
    plaintext
    0.25
    åħĨ
    0.25
     GiriÅŁ
    0.25
    æĹłå£°
    0.25
    åĵŃ
    0.25
    åľ°çĤ¹
    0.24
    Activations Density 0.137%

    No Known Activations