© 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. 22620
    Prev
    Next
    INDEX
    Explanations

    hypertension

    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
    çļĦä¼ĺåĬ¿
    -0.27
     advantage
    -0.26
    lements
    -0.26
    åĺĺ
    -0.25
    ä¼ĺåĬ¿
    -0.25
     intact
    -0.25
    ilha
    -0.25
    ä½Ĩæĺ¯ä»ĸ
    -0.24
    adv
    -0.24
    VertexBuffer
    -0.24
    POSITIVE LOGITS
    Associate
    0.27
     Associate
    0.27
    ini
    0.26
     Statement
    0.26
    _PROP
    0.25
    è°ģéĥ½
    0.25
    	Description
    0.24
    _STMT
    0.24
    ×ĵ×Ļ×Ŀ
    0.24
     Statements
    0.23
    Activations Density 0.006%

    No Known Activations