© 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. 23035
    Prev
    Next
    INDEX
    Explanations

    War

    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
    çģ«
    -0.31
    mant
    -0.27
    usted
    -0.26
    gel
    -0.25
    ITAL
    -0.25
    æ³ķå¾ĭ顾éĹ®
    -0.24
    demo
    -0.24
    满足
    -0.24
    urch
    -0.24
    åı¶åŃIJ
    -0.24
    POSITIVE LOGITS
    为ä¼ģä¸ļ
    0.28
     Fore
    0.26
    æĤ²åĵĢ
    0.25
    leta
    0.25
    _TE
    0.24
     fore
    0.24
    ieder
    0.24
    éĽĨåĽ¢èĤ¡ä»½
    0.24
    èŁĭ
    0.24
    ijing
    0.23
    Activations Density 0.002%

    No Known Activations