© 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. 12-TRANSCODER-HP
    7. 24102
    Prev
    Next
    INDEX
    Explanations

    Initialisms/Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    NA
    -0.28
    ç»Īç»ĵ
    -0.27
     Analog
    -0.26
    istical
    -0.26
    coholic
    -0.25
    licity
    -0.25
    å¾Ĺ
    -0.24
     Äijình
    -0.24
    åĨĹ
    -0.24
    avior
    -0.24
    POSITIVE LOGITS
    ongs
    0.30
    åIJĪä½ľåįıè®®
    0.28
    ç©¿è¡£
    0.27
    ouch
    0.27
    {\"
    0.26
    ','');↵
    0.26
    ignite
    0.25
    çĺ©
    0.25
    åIJĪä½ľåħ³ç³»
    0.25
    缺åı£
    0.25
    Activations Density 0.002%

    No Known Activations