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. 1-TRANSCODER-HP
    4. 9
    Prev
    Next
    INDEX
    Explanations

    There isn’t enough evidence to infer its feature, as it never activates in the provided text.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_1.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.1.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fine
    -0.28
    绪
    -0.27
     QDialog
    -0.26
    ewire
    -0.26
    icine
    -0.25
    æŁĶ
    -0.25
    etch
    -0.25
    çĸ
    -0.24
    顺çķħ
    -0.24
    æīįçŁ¥éģĵ
    -0.24
    POSITIVE LOGITS
    Ont
    0.29
    æĢģ度
    0.28
    groupName
    0.27
    aeda
    0.26
    .xls
    0.25
    {name
    0.25
    issing
    0.25
    æŀĦæĪIJäºĨ
    0.25
    è´¸
    0.25
    ÑĪÑĥ
    0.25
    Activations Density 0.329%

    No Known Activations

    This feature has no known activations.