© 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. 87597
    Prev
    Next
    INDEX
    Explanations

    since

    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
    svp
    -0.29
     hybrids
    -0.25
     already
    -0.25
    äºĭå®ŀ
    -0.24
    ErrorException
    -0.24
    оÑģÑĤÑĮ
    -0.24
     cushion
    -0.24
     Already
    -0.24
    éŃĭ
    -0.23
    æ¸ij
    -0.23
    POSITIVE LOGITS
    åİ¥
    0.29
    çļĦéĤ£ä¸Ģ
    0.26
    ake
    0.26
    éĤ£ä¸ĢåĪ»
    0.26
    缼
    0.26
     records
    0.26
    ento
    0.25
    ãģĹãģ¦ãģįãģŁ
    0.25
    èĩ³ä¸Ĭ
    0.25
    records
    0.25
    Activations Density 0.078%

    No Known Activations