© 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. 32-TRANSCODER-HP
    7. 44119
    Prev
    Next
    INDEX
    Explanations

    dual

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æľīæĿ¡ä»¶
    -0.29
    dojo
    -0.27
    nock
    -0.27
    isRequired
    -0.26
    objs
    -0.26
    æĶ¯æĮģåĬĽåº¦
    -0.26
     contracted
    -0.25
     tactical
    -0.25
    coord
    -0.25
    -addons
    -0.24
    POSITIVE LOGITS
    åħ¨ä½ĵ
    0.32
    æĢĢçĿĢ
    0.27
    -F
    0.27
    æĬĦ
    0.27
    äº²çľ¼
    0.26
    纤
    0.25
    _unix
    0.24
    èIJ½åľ¨
    0.24
     ferment
    0.24
    ç»ıè´¹
    0.24
    Activations Density 0.008%

    No Known Activations