© 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. 20-TRANSCODER-HP
    7. 131007
    Prev
    Next
    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     tá»Ń
    -0.28
     due
    -0.27
    gı
    -0.26
    赶
    -0.26
    kı
    -0.26
    çķĮçļĦ
    -0.25
    åĩij
    -0.25
    æłĩå¿Ĺ
    -0.25
    ä¸įå¾Ĺ
    -0.24
    ayı
    -0.24
    POSITIVE LOGITS
    èĵ¬åĭĥ
    0.27
    yth
    0.27
     snapchat
    0.26
     whit
    0.26
    ä½Ĩ她
    0.26
    éĩijéĴ±
    0.26
    esus
    0.25
    oes
    0.25
    åıªè¦ģä½ł
    0.25
    ä½Ĩ对äºİ
    0.25
    Activations Density 26.618%

    No Known Activations