© 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. 162836
    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
     abroad
    -0.29
     below
    -0.27
    /Framework
    -0.27
    ä¸ĭä¾Ĩ
    -0.25
    -ab
    -0.25
     alone
    -0.25
    -ins
    -0.24
    éĸ£
    -0.23
    BEST
    -0.23
    hower
    -0.23
    POSITIVE LOGITS
    è¡¥åģ¿
    0.29
    æ³Ľ
    0.28
    æĺĵ
    0.28
    è§ģ
    0.28
     compens
    0.26
    íį¼
    0.26
    éĻIJ
    0.26
    éĢĤ
    0.25
    æĮ¯
    0.25
    计ç®Ĺ
    0.25
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.