© 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. 30480
    Prev
    Next
    INDEX
    Explanations

    dis

    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
    æķ¢
    -0.28
    .Experimental
    -0.28
    oure
    -0.28
    å§Ķ
    -0.27
    sonian
    -0.26
    quier
    -0.26
    lette
    -0.25
     transcript
    -0.24
     compressor
    -0.24
    åĩº
    -0.24
    POSITIVE LOGITS
    賦
    0.28
    awan
    0.27
    èµĭ
    0.27
    actionDate
    0.27
    æĸ°éĹ»ç½ij
    0.26
    è¡Ķ
    0.25
    ÐĶÐķ
    0.25
    æĹłè§Ĩ
    0.25
     Murdoch
    0.25
     imprison
    0.25
    Activations Density 1.070%

    No Known Activations