© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29145
    Prev
    Next
    INDEX
    Explanations

    heating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ø·ÙĨ
    -0.30
    ç²Ĵ
    -0.29
     discrimin
    -0.27
    æĸĻ
    -0.26
    å±ı
    -0.26
    гÑĢамм
    -0.25
    æĴŀ
    -0.24
     pet
    -0.24
     wired
    -0.24
     NT
    -0.24
    POSITIVE LOGITS
    ảo
    0.27
    chor
    0.26
    sov
    0.26
    ä¸Ģè§Ĵ
    0.25
    é«ĺæłĩåĩĨ
    0.25
    è¿ĩå¹´
    0.25
    ä¹ĭ举
    0.24
    cka
    0.24
    maids
    0.24
    anged
    0.24
    Activations Density 1.069%

    No Known Activations