© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7478
    Prev
    Next
    INDEX
    Explanations

    migrate

    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
    ãģĵãģ¨
    -0.32
     Ñģобой
    -0.28
    ä¸Ģ个éĩįè¦ģ
    -0.27
    åı¥è¯Ŀ
    -0.26
    ãģĵãģ¨ãģ§ãģĻ
    -0.26
    ä¸Ģ个éĹ®é¢ĺ
    -0.25
    ä¹ĭä½ľ
    -0.24
    points
    -0.24
    éĩįè¦ģåĨħ容
    -0.24
    nth
    -0.24
    POSITIVE LOGITS
     cycles
    0.24
     patterns
    0.24
    ures
    0.23
    -backed
    0.23
     cycling
    0.23
    ä¸įä¿¡
    0.23
    èľ·
    0.22
     adel
    0.22
    bservable
    0.22
    	cm
    0.22
    Activations Density 2.248%

    No Known Activations