© 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. 14-TRANSCODER-HP
    7. 41658
    Prev
    Next
    INDEX
    Explanations

    variations of "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    驹
    -0.27
    addChild
    -0.26
    åĨįä¸Ģ次
    -0.26
     Lit
    -0.25
    çĦIJ
    -0.25
     lit
    -0.24
     WARRANTIES
    -0.24
    å¾ħ
    -0.23
    ·»
    -0.23
    ä¸īåĪĨä¹ĭä¸Ģ
    -0.23
    POSITIVE LOGITS
    yg
    0.35
    åĪĩ
    0.31
    eri
    0.29
    upt
    0.27
     :'
    0.27
    ëıĦ
    0.27
    rts
    0.26
    æĿİåħĪçĶŁ
    0.26
    phin
    0.26
    åıĹ害
    0.25
    Activations Density 0.046%

    No Known Activations