© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 44088
    Prev
    Next
    INDEX
    Explanations

    ability

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¿Ļä¸ĢçĤ¹
    -0.29
    è¿Ļç§įæĸ¹å¼ı
    -0.28
    è¿Ļç§įæĥħåĨµ
    -0.26
    è§ĦåĪĻ
    -0.26
    uling
    -0.26
    ihilation
    -0.26
    habi
    -0.25
    è·¯åĨµ
    -0.25
    ableObject
    -0.25
    åŁºç¡Ģ设æĸ½
    -0.25
    POSITIVE LOGITS
     level
    0.32
     retained
    0.30
     levels
    0.29
     beyond
    0.29
    ç¬ŀ
    0.28
    Levels
    0.28
     to
    0.27
    retain
    0.27
     gained
    0.27
    .Level
    0.27
    Activations Density 0.014%

    No Known Activations