© 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. 22-TRANSCODER-HP
    7. 98361
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    techn
    -0.26
    è¿Ļ项
    -0.25
    çĻ¾ç§ij
    -0.25
    éĢļçķħ
    -0.24
    eter
    -0.24
    æ¼ıæ´ŀ
    -0.23
    large
    -0.23
    身å¿ĥåģ¥åº·
    -0.23
    ostream
    -0.23
    expression
    -0.22
    POSITIVE LOGITS
    nis
    0.29
    IÃĵN
    0.27
    çĤİ
    0.26
    对æłĩ
    0.25
    nÃŃ
    0.24
    nio
    0.24
    两款
    0.24
     Panel
    0.23
    å°±ä¸įèĥ½
    0.23
    ucer
    0.23
    Activations Density 0.829%

    No Known Activations

    This feature has no known activations.