© 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. 129416
    Prev
    Next
    INDEX
    Explanations

    Web snippets and 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
     Ren
    -0.04
     Bo
    -0.04
     Tod
    -0.04
     hier
    -0.04
    Function
    -0.04
     McL
    -0.03
     Re
    -0.03
     function
    -0.03
    odium
    -0.03
    Ĥ¬
    -0.03
    POSITIVE LOGITS
    ä¸Ģå¹ķ
    0.04
    anager
    0.04
    æ¶Ī失äºĨ
    0.04
    Ãłn
    0.04
    å®ī举
    0.04
    /Common
    0.04
    é¢ĨåĨĽ
    0.04
    æĪij们å°Ĩ
    0.04
    ;break
    0.04
    æĥĬåĸľ
    0.04
    Activations Density 0.001%

    No Known Activations