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. 47142
    Prev
    Next
    INDEX
    Explanations

    become

    np_max-act · gemini-2.0-flash

    constructions that describe someone or something transitioning into a new state or condition.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
    artz
    -0.36
    ä½ĵè´¨
    -0.30
    iants
    -0.28
    anz
    -0.28
    çĨĻ
    -0.27
     family
    -0.26
    ç¹ĩ
    -0.26
    Family
    -0.26
     Family
    -0.25
    ença
    -0.25
    POSITIVE LOGITS
     deport
    0.28
     automatic
    0.26
    åĪĽ
    0.26
    Unnamed
    0.26
    unn
    0.25
    æ²ĥå°Ķ
    0.25
    instant
    0.24
     rede
    0.24
     Bri
    0.24
     instant
    0.24
    Activations Density 0.064%

    No Known Activations