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. 7-TRANSCODER-HP
    4. 98041
    Prev
    Next
    INDEX
    Explanations

    legal/rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èįª
    -0.26
    ï¼ģ');↵
    -0.25
    第äºĮ天
    -0.25
    sus
    -0.24
    UI
    -0.24
    æĺİ天
    -0.24
     unst
    -0.24
    å¯ĮåĬĽ
    -0.24
    VID
    -0.23
    Pol
    -0.23
    POSITIVE LOGITS
    AINED
    0.30
    ieten
    0.30
    cade
    0.27
    abant
    0.27
    rections
    0.26
     eyebrows
    0.25
    BAT
    0.25
    çĤ¹çĩĥ
    0.24
    esz
    0.24
    尽头
    0.24
    Activations Density 0.001%

    No Known Activations