© 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. 40584
    Prev
    Next
    INDEX
    Explanations

    invent

    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
    æĬĴ
    -0.27
    /schema
    -0.25
    enerated
    -0.25
     unto
    -0.25
    ä¹ĭ声
    -0.24
    pired
    -0.24
     Spear
    -0.24
    iegel
    -0.23
    äºĨè¿ĩæĿ¥
    -0.23
    æĮ¯åħ´
    -0.23
    POSITIVE LOGITS
    çĹĩ
    0.28
    ï¼ģ↵↵↵↵
    0.27
    leaders
    0.26
    ism
    0.25
    ione
    0.25
    oids
    0.25
    主ä¹ī
    0.24
    è¿Ļ对
    0.24
    ewidth
    0.24
    arger
    0.24
    Activations Density 2.756%

    No Known Activations