© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95740
    Prev
    Next
    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åı²
    -0.31
    å®ĺ
    -0.31
    ç¥ŀ
    -0.28
     Nev
    -0.28
    主æĦı
    -0.28
    ä¸įæŃ»
    -0.27
    å¦Ī
    -0.26
    &page
    -0.26
     BIT
    -0.26
    çĮ®
    -0.26
    POSITIVE LOGITS
    ooth
    0.30
    chnitt
    0.28
    ethyst
    0.27
    ioned
    0.26
    ocard
    0.25
    -centered
    0.24
     much
    0.24
    绣çŃ¹æİ¨è¿Ľ
    0.24
    Recogn
    0.23
     sixth
    0.23
    Activations Density 0.101%

    No Known Activations