© 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. 22-TRANSCODER-HP
    7. 87640
    Prev
    Next
    INDEX
    Explanations

    previous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥķãĤ©
    -0.24
     Warm
    -0.24
    Warm
    -0.24
    ório
    -0.24
    ãģĵãģ¨ãģĮå¤ļãģĦ
    -0.24
     principio
    -0.24
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.24
    æľĢ常è§ģçļĦ
    -0.24
    ovo
    -0.23
     doÄŁ
    -0.23
    POSITIVE LOGITS
    大大å°ı
    0.29
     hoof
    0.27
     slides
    0.27
    HOOK
    0.26
    è¶Ł
    0.26
     pal
    0.25
     plast
    0.24
    è¯įæĿ¡
    0.24
     hurdles
    0.24
    ä¸Ńåħ³
    0.24
    Activations Density 0.010%

    No Known Activations