© 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. 88300
    Prev
    Next
    INDEX
    Explanations

    beginning of articles/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
    碼
    -0.26
    èĤ¡æľ¬
    -0.25
    åij
    -0.25
     anticip
    -0.25
     ones
    -0.24
    norm
    -0.23
     infer
    -0.23
    åºĩ
    -0.23
     chạm
    -0.23
    è§ĦèĮĥåĮĸ
    -0.22
    POSITIVE LOGITS
    åħ¨éķĩ
    0.28
    alis
    0.25
    éĴ«
    0.24
     sacrificed
    0.23
    å¿ı
    0.23
    Ñĭм
    0.23
    ä»»
    0.23
    æĿijéķĩ
    0.23
    éķĩåħļå§Ķ
    0.23
    libs
    0.22
    Activations Density 0.001%

    No Known Activations