© 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. 9333
    Prev
    Next
    INDEX
    Explanations

    just

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éĢ
    -0.27
    aut
    -0.27
    åıĤ
    -0.26
    èĩªä¸»
    -0.26
     crow
    -0.25
     Crow
    -0.25
    ãģ¾ãģ¨ãĤģ
    -0.25
    ive
    -0.25
    3
    -0.24
    His
    -0.24
    POSITIVE LOGITS
    ä¸ĢåĽ¢
    0.27
    èĥ½ä½¿
    0.25
    IService
    0.25
    å±ĢéĻIJäºİ
    0.25
     Ops
    0.25
    ONES
    0.25
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.24
    %/
    0.24
    åıªçŁ¥éģĵ
    0.24
    +":
    0.24
    Activations Density 0.272%

    No Known Activations