© 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. 18-TRANSCODER-HP
    7. 89888
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é«ĺ强度
    -0.26
     humour
    -0.26
    /Page
    -0.25
     Dep
    -0.24
    å¼ķåıijäºĨ
    -0.23
    å¹ħ
    -0.23
    æĶ¹éĿ©å§Ķ
    -0.23
     Pale
    -0.23
    rase
    -0.23
     undone
    -0.23
    POSITIVE LOGITS
    finger
    0.25
    ãĥ³ãĤ°
    0.25
    å·¥ä½ľå®¤
    0.24
     Guards
    0.24
     ÑģеÑĢии
    0.24
     ÑįкÑģп
    0.24
    à¹Ģà¸Ńà¸ĩ
    0.23
     tab
    0.23
     Jenkins
    0.23
    æ·¹
    0.23
    Activations Density 1.597%

    No Known Activations

    This feature has no known activations.