© 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. 23104
    Prev
    Next
    INDEX
    Explanations

    Math and algorithms

    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
    ade
    -0.31
    rink
    -0.28
     Twe
    -0.25
     kin
    -0.24
     dipping
    -0.24
     STATUS
    -0.23
    åİ»äºĨ
    -0.23
    	Me
    -0.23
    nil
    -0.23
    icate
    -0.23
    POSITIVE LOGITS
    çļĦè¦ģæ±Ĥ
    0.29
    etz
    0.28
    å·¥ç¨ĭ建设
    0.28
     vista
    0.26
    ç¢Ľ
    0.26
    çļĦ好
    0.24
    æ¼ĶåĮĸ
    0.24
    çĪ¶
    0.24
    å«ģ
    0.24
    yers
    0.23
    Activations Density 0.002%

    No Known Activations