© 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. 7756
    Prev
    Next
    INDEX
    Explanations

    heart, artery

    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
    ...↵↵
    -0.27
    -legged
    -0.27
     anonymously
    -0.27
    åĵĤ
    -0.25
    æįķæįī
    -0.25
    ocache
    -0.24
    _ESCAPE
    -0.24
     dét
    -0.23
    bearing
    -0.23
    lane
    -0.23
    POSITIVE LOGITS
    å¿ĥæĦ¿
    0.28
    个人è§ĤçĤ¹
    0.27
    äºĨ
    0.25
    ç¢İ
    0.25
    大æ°Ķ
    0.25
    èĭ´
    0.24
    裸
    0.24
    ÅŁa
    0.24
    æĻŀ
    0.24
    Sibling
    0.24
    Activations Density 0.165%

    No Known Activations