© 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. 27-TRANSCODER-HP
    7. 7942
    Prev
    Next
    INDEX
    Explanations

    Month names

    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
    Negative Logits
    igin
    -0.27
    BUR
    -0.26
    ninger
    -0.25
    úng
    -0.25
    iore
    -0.25
     AUG
    -0.24
    æĥ³è±¡
    -0.24
    umbling
    -0.24
    uating
    -0.24
     thinks
    -0.24
    POSITIVE LOGITS
    ä¸Ģ次æĢ§
    0.33
     accommod
    0.27
    Serialized
    0.27
    peare
    0.27
    éĿ¢å¯¹éĿ¢
    0.25
    æīĺ管
    0.25
    atin
    0.25
    ographies
    0.25
    ä¸Ģ次
    0.24
    paragus
    0.24
    Activations Density 0.002%

    No Known Activations