© 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. 8951
    Prev
    Next
    INDEX
    Explanations

    well

    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
    纤
    -0.28
     kê
    -0.27
    æĦŁåıĹåĪ°äºĨ
    -0.26
    acie
    -0.24
    饷
    -0.24
    ä¹Łä¸įçŁ¥éģĵ
    -0.24
     decrement
    -0.24
    ä¹Łæĺ¯ä¸Ģ个
    -0.24
     Ballard
    -0.24
    åŃĶ
    -0.24
    POSITIVE LOGITS
    urst
    0.28
    åī¯æĢ»
    0.28
    rames
    0.28
    chy
    0.27
    (False
    0.26
     survival
    0.26
     enough
    0.26
    æĭĻ
    0.25
    åIJį声
    0.25
    _TI
    0.25
    Activations Density 0.058%

    No Known Activations