© 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. 57647
    Prev
    Next
    INDEX
    Explanations

    including

    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
    RTL
    -0.27
    lor
    -0.26
    ä¹Łæĺ¯å¦ĤæѤ
    -0.26
    .until
    -0.26
    åĺİ
    -0.25
    ä»Ģä¹Īéĥ½ä¸į
    -0.25
    éĺĬ
    -0.24
    odge
    -0.24
    管çIJĨæĿ¡ä¾ĭ
    -0.24
    CR
    -0.24
    POSITIVE LOGITS
     prominent
    0.38
     notable
    0.34
     prominently
    0.29
    èijĹåIJį
    0.29
     important
    0.28
    tap
    0.28
    éĩįè¦ģ
    0.28
    åŁİå¸ĤçļĦ
    0.27
    ä¸Ģ大
    0.27
    å¾Īéĩįè¦ģ
    0.27
    Activations Density 0.016%

    No Known Activations