© 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. 24-TRANSCODER-HP
    7. 150040
    Prev
    Next
    INDEX
    Explanations

    take

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isti
    -0.29
    èħĮ
    -0.26
    é«ĺè´¨éĩı
    -0.25
    è¯Ń
    -0.25
    å¤Ł
    -0.25
    OBJECT
    -0.25
    æĢĿãģĦåĩº
    -0.25
    çī¹æĸ¯
    -0.24
    è¯Ĵ
    -0.24
    rgba
    -0.24
    POSITIVE LOGITS
     simple
    0.33
    ç®ĢåįķçļĦ
    0.28
    æŁIJ个
    0.28
    åįķ纯çļĦ
    0.27
     simplest
    0.27
     first
    0.27
    é¦ĸåħĪæĺ¯
    0.26
    ãģ¾ãģļ
    0.26
     firstly
    0.26
    -cond
    0.26
    Activations Density 0.138%

    No Known Activations