© 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. 33-TRANSCODER-HP
    7. 53875
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŦ
    -0.28
    umer
    -0.25
    yy
    -0.25
    ä¸ĢæľŁ
    -0.25
    ä¸Ģ件
    -0.24
     Common
    -0.24
    å¿ĥæĢĿ
    -0.24
    Common
    -0.24
    icum
    -0.24
     sil
    -0.23
    POSITIVE LOGITS
    1
    0.30
    2
    0.27
    3
    0.25
    å°ĨæĿ¥
    0.25
    ç«ĭä½ĵ
    0.24
     Pills
    0.23
    åĩł
    0.23
    0
    0.23
     Redistributions
    0.23
    åIJĮæĻĤ
    0.23
    Activations Density 0.009%

    No Known Activations