© 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. 22-TRANSCODER-HP
    7. 97519
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹ĥèĩ³
    -0.31
    çĶļèĩ³
    -0.28
    ком
    -0.28
    çļĦæ¨¡æł·
    -0.26
    jud
    -0.25
    ä¸īçĻ¾
    -0.25
     especially
    -0.24
     pris
    -0.24
    çĶļèĩ³è¿ĺ
    -0.24
    modele
    -0.24
    POSITIVE LOGITS
    edBy
    0.31
     Whitney
    0.26
    ç²¾
    0.26
    æ¥ł
    0.24
    alsy
    0.24
    oin
    0.23
    enal
    0.23
    ä¸ĬåįĪ
    0.23
    å°ģ
    0.23
    pte
    0.23
    Activations Density 0.004%

    No Known Activations