© 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. 129754
    Prev
    Next
    INDEX
    Explanations

    General language

    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
    è¯ķçĤ¹
    -0.27
    æ¿Ģç´ł
    -0.26
    (mut
    -0.26
    åģıå·®
    -0.25
    ä¾ł
    -0.25
    vt
    -0.24
    åįıä¼ļä¼ļéķ¿
    -0.24
    çģµæ´»æĢ§
    -0.24
    广éĺĶ
    -0.24
     resultCode
    -0.24
    POSITIVE LOGITS
    ä¸Ģä½ĵåĮĸ
    0.24
    檫
    0.24
     occupying
    0.23
    å¿ĥéĩĮ
    0.23
    	range
    0.23
    ç½ij约
    0.23
    :id
    0.23
     dancing
    0.23
    اÙĦÙħ
    0.23
    à¸ļ
    0.23
    Activations Density 0.003%

    No Known Activations