© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161834
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    å®ļ
    -0.27
    æ´ĭæ´ĭ
    -0.27
     Core
    -0.26
    è¿ĶåĽŀæIJľçĭIJ
    -0.26
    å®ļéĩı
    -0.25
    çĥĪ
    -0.25
     Voice
    -0.25
    æĮ£æīİ
    -0.24
     separ
    -0.23
     CP
    -0.23
    POSITIVE LOGITS
    rog
    0.32
    umn
    0.28
    ileged
    0.27
    enk
    0.27
    è³ŀ
    0.26
    è¿·ä½ł
    0.26
    ButtonType
    0.25
    ita
    0.25
    holder
    0.25
    ','=',
    0.25
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.