© 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. 88125
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    å¾µ
    -0.32
    shaw
    -0.26
    æİ¡
    -0.26
     меÑĢ
    -0.26
    eration
    -0.26
    شا
    -0.26
    ification
    -0.25
    å¾ģ
    -0.25
    åľĪ
    -0.25
    alent
    -0.25
    POSITIVE LOGITS
    asca
    0.27
    è·¸
    0.27
    åĽŀåĪ°å®¶
    0.26
    çļĦåİĭåĬĽ
    0.26
     fort
    0.25
    egt
    0.25
    oze
    0.25
    åıĪä¸Ģ次
    0.25
    upe
    0.24
    oger
    0.24
    Activations Density 0.018%

    No Known Activations