© 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. 20-TRANSCODER-HP
    7. 63055
    Prev
    Next
    INDEX
    Explanations

    sound

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vidence
    -0.27
    ivy
    -0.26
    .NotFound
    -0.26
     spur
    -0.25
     plunge
    -0.24
    以åıĬåħ¶ä»ĸ
    -0.24
     teen
    -0.24
     teens
    -0.24
    -bg
    -0.23
     timetable
    -0.23
    POSITIVE LOGITS
    ç²Ĵ
    0.27
    reh
    0.25
    mart
    0.25
     fraught
    0.24
    çĨŁ
    0.24
    è¼
    0.24
    å·¥ä½ľå²Ĺä½į
    0.24
    æĢĿãģĨ
    0.24
    ủ
    0.24
    ç½ijçĤ¹
    0.23
    Activations Density 3.313%

    No Known Activations