© 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. 88515
    Prev
    Next
    INDEX
    Explanations

    like of

    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
    æĥłåıĬ
    -0.29
    ç½²
    -0.25
    UNCH
    -0.24
     Skate
    -0.24
    æľīéĻIJ
    -0.24
    Snow
    -0.24
     coherence
    -0.24
     erm
    -0.23
    è¦Ĩ
    -0.23
     corporations
    -0.23
    POSITIVE LOGITS
    èѦ
    0.28
     gab
    0.27
    夫
    0.25
    éĵĥ
    0.23
    ä¸ĢæŃ¥
    0.23
    schema
    0.23
    achten
    0.23
     deb
    0.23
    /current
    0.23
    åģļå®Į
    0.23
    Activations Density 16.794%

    No Known Activations