© 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. 19-TRANSCODER-HP
    7. 9478
    Prev
    Next
    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <typeof
    -0.27
    Ŀå§ĭ
    -0.27
    åį´ä¸į
    -0.27
     sqr
    -0.26
    .Permission
    -0.26
    ä¸ĸ家
    -0.26
     illum
    -0.26
    zet
    -0.25
    cycl
    -0.24
    ä¸įçĶ±
    -0.24
    POSITIVE LOGITS
    æĻı
    0.29
    loff
    0.26
     popping
    0.26
    mania
    0.26
    ÙĨÙĬ
    0.25
    æį»
    0.25
    转æį¢
    0.25
     backstage
    0.25
    éo
    0.24
    ulk
    0.24
    Activations Density 0.065%

    No Known Activations