© 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. 29342
    Prev
    Next
    INDEX
    Explanations

    console

    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
    æį¢æĪIJ
    -0.28
    BITS
    -0.26
     dra
    -0.26
    ŀæĢ§
    -0.26
    åIJij社ä¼ļ
    -0.25
    fred
    -0.25
    )[
    -0.24
    èĩªåľ¨
    -0.24
    åıĺäºĨ
    -0.24
    æį¢
    -0.24
    POSITIVE LOGITS
    olders
    0.28
    urse
    0.27
    heels
    0.27
    upe
    0.26
    ción
    0.26
     pres
    0.25
    illos
    0.25
    æ¯ĽåŃĶ
    0.24
    åĪºæ¿Ģ
    0.24
    èĭĵ
    0.24
    Activations Density 0.712%

    No Known Activations