© 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. 8243
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    æĽ´éĩįè¦ģçļĦ
    -0.30
    å°¤åħ¶
    -0.26
     especialmente
    -0.25
    åį¤
    -0.25
     sucesso
    -0.25
     medida
    -0.24
    .pref
    -0.24
    _expect
    -0.24
     pronto
    -0.24
     entity
    -0.24
    POSITIVE LOGITS
     two
    0.33
    ä¸Ģ个个
    0.32
    ä¸Ģ个æĺ¯
    0.31
    两个
    0.30
    agle
    0.27
    们çļĦ
    0.26
    ä¸¤åľ°
    0.26
     numerator
    0.26
    ä¸ī个æĸ¹éĿ¢
    0.26
    two
    0.25
    Activations Density 0.018%

    No Known Activations