© 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. 41700
    Prev
    Next
    INDEX
    Explanations

    Oligonucleotides/primers

    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
     debug
    -0.26
    精确
    -0.25
    å°½åı¯èĥ½
    -0.24
    ç²īæľ«
    -0.24
     Primitive
    -0.24
    ValuePair
    -0.24
    çĸĹ
    -0.24
    çī¯
    -0.23
    _sn
    -0.23
     discrete
    -0.23
    POSITIVE LOGITS
    ']}'
    0.28
    gı
    0.26
    eres
    0.26
    imity
    0.26
    ISK
    0.25
     sqlSession
    0.25
    elry
    0.24
    å¹´ä¹ĭä¹ħ
    0.24
    å®ŀè´¨æĢ§
    0.24
    foy
    0.24
    Activations Density 0.058%

    No Known Activations