© 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. 12-TRANSCODER-HP
    7. 23619
    Prev
    Next
    INDEX
    Explanations

    transport

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quarters
    -0.31
    ä¸Ģ棵
    -0.27
    æĻ¶
    -0.26
    æĿ¥è®¿
    -0.25
    æŶèĬĤ
    -0.25
    详ç»ĨäºĨ解
    -0.25
    çĹĽ
    -0.25
     Sys
    -0.25
    å®¡æŁ¥
    -0.24
     accessed
    -0.24
    POSITIVE LOGITS
    lder
    0.30
     splice
    0.28
    filme
    0.27
    -spot
    0.25
    pired
    0.25
    èģĬ
    0.25
    æĮĤéĴ©
    0.25
    groupBox
    0.24
    å°ijäºĨ
    0.24
    äºĨåĩł
    0.24
    Activations Density 0.031%

    No Known Activations