© 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. 29519
    Prev
    Next
    INDEX
    Explanations

    short words

    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
    Quality
    -0.29
    æ¸ħ
    -0.28
    è´¨éĩı
    -0.27
    è¦ģçĤ¹
    -0.27
    æ´»åĬ¨
    -0.26
     quality
    -0.26
    èĥ½å¾ĹåĪ°
    -0.26
     Quality
    -0.26
    quality
    -0.25
    èĪªéģĵ
    -0.25
    POSITIVE LOGITS
    æ®ĩ
    0.26
     rar
    0.26
    _po
    0.26
     ado
    0.25
    onders
    0.25
    oplevel
    0.25
    æīĵæĸŃ
    0.25
    ISON
    0.24
    æ¯Ļ
    0.24
    .Exists
    0.24
    Activations Density 1.359%

    No Known Activations