© 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. 98125
    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
    ãĢģãĢĮ
    -0.26
    ulk
    -0.26
    olest
    -0.26
    ä¸Ģæł·çļĦ
    -0.25
    елÑı
    -0.25
     UIT
    -0.25
    溥
    -0.24
    é¹ij
    -0.24
    å·¨æĺŁ
    -0.24
    ect
    -0.24
    POSITIVE LOGITS
    /conf
    0.27
    å®Į
    0.26
     Conf
    0.26
    BSITE
    0.25
    >[]
    0.25
    opher
    0.24
     hurd
    0.24
    åħ¨éĿ¢
    0.23
    å±±æĿij
    0.23
    ä¸įçĶ¨æĭħå¿ĥ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.