© 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. 98166
    Prev
    Next
    INDEX
    Explanations

    which

    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
     WARRANTIES
    -0.27
    tÃŃ
    -0.26
    åĴ¨
    -0.24
     branches
    -0.24
     Communic
    -0.24
    itecture
    -0.23
    æĹħè¡Į
    -0.23
     Truyá»ģn
    -0.23
    Communic
    -0.23
     Volunteers
    -0.23
    POSITIVE LOGITS
    å½ĵæŶ
    0.32
    ingly
    0.32
    jer
    0.27
    å½ĵæŶçļĦ
    0.27
    çķ¶æĻĤ
    0.26
    æİĴéĺŁ
    0.26
    ç¥ĸ
    0.26
     famously
    0.25
    xffff
    0.25
     wasn
    0.24
    Activations Density 0.019%

    No Known Activations