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. 10394
    Prev
    Next
    INDEX
    Explanations

    build-up and down

    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
    ä¸ĢæĹ¥
    -0.26
    ChangeListener
    -0.26
    èļ¤
    -0.24
    ä¸į论æĺ¯
    -0.24
    ','');↵
    -0.24
    ר׼×Ķ
    -0.24
     tslint
    -0.24
    qli
    -0.23
    éĴį
    -0.23
    COVERY
    -0.23
    POSITIVE LOGITS
     disput
    0.26
    horn
    0.26
    stdbool
    0.26
     './../../
    0.25
     sheet
    0.25
    kos
    0.25
     invol
    0.24
     tog
    0.24
    åħĭæĸ¯
    0.24
    gor
    0.24
    Activations Density 0.001%

    No Known Activations