© 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. 9-TRANSCODER-HP
    7. 29913
    Prev
    Next
    INDEX
    Explanations

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Locker
    -0.30
     disorder
    -0.26
    åģļä»Ģä¹Ī
    -0.25
     hẳn
    -0.25
     stom
    -0.25
    å®ļäºĨ
    -0.24
    -review
    -0.24
    egin
    -0.23
    =[]č↵
    -0.23
     underwent
    -0.23
    POSITIVE LOGITS
    å¢Ļå£ģ
    0.26
    azing
    0.26
    sold
    0.25
    ä½łæĺ¯
    0.25
    isters
    0.25
    åºł
    0.25
    à¹Ħว
    0.25
    uart
    0.25
     Column
    0.24
    UIS
    0.24
    Activations Density 0.712%

    No Known Activations