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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 228
    Prev
    Next
    INDEX
    Explanations

    Bowls, sports, and bowel issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lấy
    -0.28
    uja
    -0.27
    åĪłéĻ¤æĪIJåĬŁ
    -0.25
    åıĸ
    -0.25
    注æĺİåĩºå¤Ħ
    -0.24
    è¡Ģ液
    -0.24
    ptr
    -0.23
     Hem
    -0.23
    Sk
    -0.23
     setC
    -0.23
    POSITIVE LOGITS
    ayer
    0.31
    trys
    0.26
    /wp
    0.25
    ä»ĸä»¬åľ¨
    0.24
    izen
    0.23
    æ§Į
    0.23
    Invite
    0.23
    -live
    0.23
     Taste
    0.23
    svp
    0.22
    Activations Density 0.024%

    No Known Activations