© 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. 89028
    Prev
    Next
    INDEX
    Explanations

    Generic web content fragments

    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
    ç»ıèIJ¥èĮĥåĽ´
    -0.25
    è¾¹çķĮ
    -0.24
    à¸Ĥà¸Ńà¸ļ
    -0.24
    æģ°å½ĵ
    -0.24
    ests
    -0.23
    anje
    -0.23
     dest
    -0.23
     percentage
    -0.23
    atter
    -0.22
    DEST
    -0.22
    POSITIVE LOGITS
    åIJĪæĪIJ
    0.27
    Õ¦
    0.26
    æľªæĪIJ
    0.25
    ship
    0.25
    desk
    0.25
    TEX
    0.25
    嵯
    0.25
    顽
    0.25
    uye
    0.24
    ragen
    0.24
    Activations Density 10.356%

    No Known Activations