© 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. 29180
    Prev
    Next
    INDEX
    Explanations

    austerity

    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
     knowledge
    -0.27
    çļĦçŁ¥è¯Ĩ
    -0.27
    elman
    -0.27
     znal
    -0.27
    çłľ
    -0.27
    .Disclaimer
    -0.25
    _INITIALIZER
    -0.25
    odox
    -0.25
    åıij表
    -0.25
     FAQ
    -0.24
    POSITIVE LOGITS
    å¤ĩ份
    0.30
    å®īæİĴ
    0.27
    plx
    0.26
    ibern
    0.26
     запиÑģ
    0.26
    aina
    0.26
    Kit
    0.25
     зап
    0.25
    èĥĮåIJİçļĦ
    0.25
    igne
    0.25
    Activations Density 0.697%

    No Known Activations