© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24030
    Prev
    Next
    INDEX
    Explanations

    shows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Cele
    -0.27
     CONDITION
    -0.26
    åģĩæĹ¥
    -0.26
    æĮĩ示
    -0.26
    aling
    -0.25
    奢
    -0.25
    asonic
    -0.24
    childs
    -0.24
    ãĤĵãģ§ãģĦãĤĭ
    -0.24
    åı¯è§Ĩ
    -0.24
    POSITIVE LOGITS
    WithEmail
    0.26
    é¡»
    0.26
    éĢļ
    0.25
    éłĪ
    0.25
    alnum
    0.25
    //{{
    0.24
    éĺµ
    0.24
    æ¶Įåħ¥
    0.24
    åĽŀæĬ¥
    0.24
    Lifetime
    0.24
    Activations Density 0.002%

    No Known Activations