© 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. 29360
    Prev
    Next
    INDEX
    Explanations

    festivals and related terms

    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
    ลà¸Ńย
    -0.28
     snap
    -0.28
     bed
    -0.27
    æıIJé«ĺ
    -0.25
    @c
    -0.25
    æıIJ
    -0.24
    æĦŁæĥħ
    -0.24
    æĬķæĶ¾
    -0.24
    ä¸īçĤ¹
    -0.24
     spark
    -0.24
    POSITIVE LOGITS
    eneg
    0.31
    SCII
    0.28
    buzz
    0.27
    è´
    0.27
    tees
    0.25
    isses
    0.25
    èģ
    0.25
    anza
    0.25
     ([[
    0.25
    èĭ§
    0.25
    Activations Density 1.925%

    No Known Activations