© 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. 9-TRANSCODER-HP
    7. 30061
    Prev
    Next
    INDEX
    Explanations

    historical context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azine
    -0.32
    éĩİ
    -0.31
    å®ĺæĸ¹
    -0.26
    assen
    -0.26
    åıĮè¾¹
    -0.25
    ationToken
    -0.25
    /ay
    -0.25
    sites
    -0.24
    æĭĴç»Ŀ
    -0.24
    ÑĢеÑģÑĤ
    -0.24
    POSITIVE LOGITS
     Pilot
    0.27
     Chancellor
    0.27
     Canadians
    0.26
    éļĶçĥŃ
    0.26
    èIJ½åľ°
    0.25
     swords
    0.24
    ä½ľåĵģåĨħ容
    0.24
     FIT
    0.24
    æĶ¹åĬ¨
    0.24
    ç©¿éĢı
    0.23
    Activations Density 10.540%

    No Known Activations