© 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. 14-TRANSCODER-HP
    7. 41295
    Prev
    Next
    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩ³ä¸Ĭ
    -0.26
    ä¼¼ä¹İæĺ¯
    -0.26
     Hwy
    -0.26
    resher
    -0.25
     faucet
    -0.24
     unl
    -0.24
    orelease
    -0.23
    mour
    -0.23
    宣称
    -0.23
    éĩįçİ°
    -0.23
    POSITIVE LOGITS
    ç§ģ人
    0.31
    æķ´ä½ĵ
    0.29
    ()='
    0.28
     home
    0.27
    iki
    0.26
    åħ¨çIJĥ
    0.26
    åıij
    0.25
     led
    0.25
     Home
    0.25
    èĤĭ
    0.25
    Activations Density 0.368%

    No Known Activations