© 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. 18-TRANSCODER-HP
    7. 89775
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»·
    -0.28
    during
    -0.25
    客æĪ·çļĦ
    -0.25
    æĦģ
    -0.24
    å¥Ĺé¤IJ
    -0.23
    åĹĴ
    -0.23
    æ³ķå¾ĭè§Ħå®ļ
    -0.23
    Mag
    -0.23
     Shoe
    -0.23
     CART
    -0.23
    POSITIVE LOGITS
    éģ¨
    0.26
    sure
    0.26
    ossal
    0.25
     sure
    0.24
    imin
    0.24
    squeeze
    0.24
    -switch
    0.24
    ä¸Ģ个éĹ®é¢ĺ
    0.24
    ousel
    0.23
     palate
    0.23
    Activations Density 6.385%

    No Known Activations

    This feature has no known activations.