© 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. 89641
    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
    holm
    -0.27
    ç§ģèĩª
    -0.26
    lund
    -0.25
     Sheldon
    -0.25
    uds
    -0.25
    ensibly
    -0.25
    ảy
    -0.24
    cult
    -0.24
    orges
    -0.24
     parten
    -0.24
    POSITIVE LOGITS
    就好åĥı
    0.26
    lift
    0.25
     BitmapFactory
    0.25
     advantage
    0.25
    çļĦä¼ĺåĬ¿
    0.25
    çĽ¸å¯¹
    0.24
    åıł
    0.24
    locale
    0.24
    /tool
    0.24
    agnost
    0.24
    Activations Density 0.157%

    No Known Activations

    This feature has no known activations.