© 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. 88459
    Prev
    Next
    INDEX
    Explanations

    months

    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
    ä¸ĸçķĮçļĦ
    -0.28
    ä¸ĸçķĮåIJĦåľ°
    -0.27
    å¹¿æ³ĽçļĦ
    -0.25
    åķĨ
    -0.25
    mot
    -0.24
    ardon
    -0.24
    instancetype
    -0.24
    åħ³éĶ®æŶåĪ»
    -0.24
    è°ı
    -0.23
    legation
    -0.23
    POSITIVE LOGITS
    Extractor
    0.26
    åģı
    0.26
    aar
    0.25
     posts
    0.25
    aks
    0.24
     trigger
    0.24
    alo
    0.24
    ×Ĺ×ķת
    0.24
    æİĮ
    0.24
     delete
    0.24
    Activations Density 0.034%

    No Known Activations