© 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. 12-TRANSCODER-HP
    7. 23622
    Prev
    Next
    INDEX
    Explanations

    medical consultations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    "title
    -0.27
    æĺŁæĺŁ
    -0.27
     wave
    -0.25
     waves
    -0.25
     VIA
    -0.24
     pass
    -0.24
    绣ä¸Ģ
    -0.24
     problematic
    -0.24
    Title
    -0.24
    _wave
    -0.24
    POSITIVE LOGITS
    ÈĽi
    0.28
    ä¹Ŀå¹´
    0.27
    èĵĦ
    0.27
    .Xaml
    0.25
     Confeder
    0.25
    alnum
    0.24
    è¿Ļä¸ī个
    0.24
    emento
    0.24
    ç»ĨèĬĤ
    0.23
    æĮļ
    0.23
    Activations Density 0.000%

    No Known Activations