© 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. 27-TRANSCODER-HP
    7. 9006
    Prev
    Next
    INDEX
    Explanations

    followed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ná»ģn
    -0.27
    å®ŀ
    -0.27
    åıĻäºĭ
    -0.27
    [code
    -0.26
    å½ĵä½ľ
    -0.25
    ä¹ĥ
    -0.25
    æľĢæĹ©çļĦ
    -0.24
    å½ĵ
    -0.24
    unge
    -0.24
    alus
    -0.24
    POSITIVE LOGITS
    ä¸Ģ个人
    0.37
    edin
    0.31
     individuals
    0.31
     lifelong
    0.29
     participants
    0.28
    两个人
    0.28
    lesc
    0.27
    åįģå¤ļå¹´
    0.26
     citizens
    0.26
     someone
    0.26
    Activations Density 0.007%

    No Known Activations