© 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. 23-TRANSCODER-HP
    7. 24860
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hal
    -0.30
    æĥ³å¿µ
    -0.25
    Coder
    -0.25
     sil
    -0.24
    æĪijçĪ±ä½ł
    -0.24
    ä¸ĢéĹª
    -0.24
     riêng
    -0.24
    ä¸Ģ次
    -0.24
    (expect
    -0.24
    è´¬
    -0.24
    POSITIVE LOGITS
    éĥ½æĺ¯
    0.33
    è¿Ļ两ç§į
    0.30
    çļĨ
    0.30
    éĥ½
    0.28
    WithPath
    0.27
    两èĢħ
    0.27
     bred
    0.26
    éĥ½åľ¨
    0.26
    åĿĩ为
    0.26
    篷
    0.25
    Activations Density 0.006%

    No Known Activations