© 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. 87299
    Prev
    Next
    INDEX
    Explanations

    disclaimer

    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
    Locker
    -0.27
    лага
    -0.26
    osal
    -0.25
    æį·
    -0.24
    åľ¨æѤä¹ĭåīį
    -0.24
     desn
    -0.23
    ä»Ĺ
    -0.23
    linger
    -0.23
     synthetic
    -0.23
    orsk
    -0.23
    POSITIVE LOGITS
    arring
    0.28
    undy
    0.27
     carefully
    0.26
    æľīéĻIJ责任
    0.25
    æ·¤
    0.25
    翦
    0.24
    irt
    0.24
    æ»ĵ
    0.24
     fis
    0.23
     CARE
    0.23
    Activations Density 0.043%

    No Known Activations