© 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. 111710
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĸı
    -0.30
     autoload
    -0.27
    é£ŀè¡Į
    -0.26
    è°ģçŁ¥éģĵ
    -0.26
    nip
    -0.26
    raison
    -0.25
     commissioners
    -0.25
    æĪijçļĦå¿ĥ
    -0.24
    iller
    -0.24
    manent
    -0.24
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.27
     viewType
    0.25
    egis
    0.24
    æĿĥ
    0.24
    讣
    0.24
    åľ¨è¿Ļç§į
    0.23
    itus
    0.23
    (resourceName
    0.23
    [:]
    0.23
    ÑĨов
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.