© 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. 20-TRANSCODER-HP
    7. 130667
    Prev
    Next
    INDEX
    Explanations

    Verb endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ人
    -0.27
    	Query
    -0.26
     regained
    -0.26
    éħ¢
    -0.26
     unto
    -0.25
    ãĤ¢ãĥ³
    -0.25
    æŃ¤æ¬¡
    -0.24
    ANC
    -0.24
    nom
    -0.24
    ça
    -0.23
    POSITIVE LOGITS
    VERR
    0.27
    eper
    0.26
    åľ¨å¤ĸ
    0.25
     integer
    0.25
     avenue
    0.25
    icles
    0.24
    igmat
    0.24
    ityEngine
    0.24
    ä¸Ģ页
    0.24
     Rou
    0.23
    Activations Density 60.618%

    No Known Activations