© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63688
    Prev
    Next
    INDEX
    Explanations

    present time

    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
    Not in Any Lists

    No Comments

    Negative Logits
    以åIJİ
    -0.28
    以å¾Į
    -0.27
     scheme
    -0.26
    é¢Ĩ
    -0.25
    å®ļ
    -0.25
     fitting
    -0.25
    atasets
    -0.24
     hÆ°á»Łng
    -0.24
    -vars
    -0.24
    Playable
    -0.23
    POSITIVE LOGITS
    ä¹Ŀåįģ
    0.28
    bounce
    0.26
    åĿļå®ļä¸į移
    0.26
     retained
    0.26
    æĶ¾ç¼ĵ
    0.25
     retains
    0.24
    纳æĸ¯
    0.24
     backed
    0.24
    æĭĩ
    0.24
    硬åĮĸ
    0.24
    Activations Density 3.696%

    No Known Activations