© 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. 106983
    Prev
    Next
    INDEX
    Explanations

    Random text strings

    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
    åıĭè°Ĭ
    -0.29
    移æ¤į
    -0.28
    ä¿¡ç®±
    -0.28
    è¢ĭåŃIJ
    -0.26
    åı£æ°´
    -0.25
    管家
    -0.24
    大家éĥ½åľ¨
    -0.24
    ä½łä¼ļ
    -0.24
    è¿ijè·Ŀ离
    -0.24
     lace
    -0.24
    POSITIVE LOGITS
    ação
    0.29
    aa
    0.28
    s
    0.27
    å¯Ĵ
    0.26
    erg
    0.26
    ers
    0.26
    sar
    0.26
     us
    0.26
    eree
    0.25
    iel
    0.25
    Activations Density 5.870%

    No Known Activations