© 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. 4-TRANSCODER-HP
    7. 138
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acci
    -0.28
    å¿ĺè®°
    -0.27
    ä½łçľĭ
    -0.26
    æĺİæĺ¾
    -0.25
    å¿ĺè®°äºĨ
    -0.24
    ä½łè¿ĺ
    -0.24
    å¿ĺäºĨ
    -0.24
    çĪIJ
    -0.24
    criptor
    -0.23
    achel
    -0.23
    POSITIVE LOGITS
    äºĴ
    0.25
    evity
    0.25
     Nay
    0.23
    monds
    0.23
    enos
    0.23
    nore
    0.23
    æľĢéĩįè¦ģçļĦ
    0.23
    enter
    0.23
    çİ©æ³ķ
    0.22
    inkle
    0.22
    Activations Density 3.039%

    No Known Activations

    This feature has no known activations.