© 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. 88986
    Prev
    Next
    INDEX
    Explanations

    Contractions

    np_max-act · gemini-2.0-flash
    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
    éľ¹
    -0.28
    tractor
    -0.28
    åĩºè½¨
    -0.25
    ordinary
    -0.24
    lint
    -0.24
    èī¯
    -0.24
    æĹ¢è¦ģ
    -0.24
    好åIJĹ
    -0.23
    èĥ½ä¸įèĥ½
    -0.23
     Yourself
    -0.23
    POSITIVE LOGITS
     bas
    0.25
     gy
    0.25
    ipop
    0.25
    ç¡IJ
    0.25
     sw
    0.25
    åŃIJ
    0.25
    çıĢ
    0.24
     [âĢ¦
    0.24
    vere
    0.24
    ardon
    0.23
    Activations Density 2.806%

    No Known Activations