© 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. 129502
    Prev
    Next
    INDEX
    Explanations

    blog posts

    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
    bjerg
    -0.27
    gap
    -0.27
    Õ®
    -0.27
    ä¸Ģåı£æ°Ķ
    -0.26
    ofi
    -0.25
    ä½ľåĵģåĨħ容
    -0.25
    å®´
    -0.25
    нÑıÑĤи
    -0.24
    orsi
    -0.24
    :]↵↵
    -0.24
    POSITIVE LOGITS
    åģ¶å°Ķ
    0.44
     occasional
    0.43
     occasionally
    0.42
     few
    0.40
     Occasionally
    0.39
     quelques
    0.38
    åĩłåı¥
    0.34
     Few
    0.33
    åĩłä¸ª
    0.33
    åĩł
    0.32
    Activations Density 0.019%

    No Known Activations