© 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. 14-TRANSCODER-HP
    7. 39931
    Prev
    Next
    INDEX
    Explanations

    future

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĽ¿ä»£
    -0.26
    ration
    -0.25
    à¸ķà¸Ńà¸ļ
    -0.25
    éĢģè¾¾
    -0.24
    æĽ¿æį¢
    -0.24
     "-//
    -0.24
    讯
    -0.24
    nih
    -0.24
     exchange
    -0.24
    osite
    -0.23
    POSITIVE LOGITS
    /ec
    0.27
     Ñįк
    0.25
    ç»Ħè£ħ
    0.25
    ä¾ĽåĽ¾
    0.25
    Ec
    0.24
    	esc
    0.24
    [l
    0.24
    éĵĢ
    0.24
    feeds
    0.24
    esthes
    0.24
    Activations Density 2.667%

    No Known Activations