© 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. 19-TRANSCODER-HP
    7. 8134
    Prev
    Next
    INDEX
    Explanations

    Code, legal, and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .'_
    -0.28
    åĨĻçĿĢ
    -0.25
    ç®Ķ
    -0.24
    åĨĻçļĦ
    -0.23
    补水
    -0.23
    æľī个
    -0.23
    åĩºæ¸¸
    -0.23
    çŃ®
    -0.23
    æĮģèĤ¡
    -0.23
    checksum
    -0.23
    POSITIVE LOGITS
    åłĤ
    0.32
    IME
    0.30
    ael
    0.28
    ime
    0.28
    人æ°Ķ
    0.26
    /close
    0.26
    Arrow
    0.25
    /manual
    0.25
    ToOne
    0.25
    就好äºĨ
    0.24
    Activations Density 0.006%

    No Known Activations