© 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. 29838
    Prev
    Next
    INDEX
    Explanations

    demographics

    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
    weak
    -0.32
    -short
    -0.28
    Weak
    -0.28
     Weak
    -0.27
    OTOS
    -0.27
    chestra
    -0.26
     Qi
    -0.26
    vetica
    -0.26
     weak
    -0.25
    udios
    -0.25
    POSITIVE LOGITS
    论
    0.33
    åĨįéĢł
    0.29
    楼ä¸ĭ
    0.27
    æĺĨæĺİ
    0.27
    æݥ触åĪ°
    0.27
    è«ĸ
    0.27
    ä½ľçĶ¨
    0.26
    nj
    0.25
    amus
    0.25
    æİīäºĨ
    0.25
    Activations Density 0.256%

    No Known Activations