© 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. 98254
    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
     MEDIA
    -0.30
    TAB
    -0.28
    =sub
    -0.27
    åĩłå¼ł
    -0.26
    falls
    -0.25
    羣åģĩ
    -0.25
    æİĴåIJį第ä¸Ģ
    -0.23
    è¿Ļå¼ł
    -0.23
    favor
    -0.23
     named
    -0.23
    POSITIVE LOGITS
    wor
    0.29
    åħ³éĶ®æĺ¯
    0.26
    çŀŃ
    0.25
    Continue
    0.25
     casualty
    0.25
    ikan
    0.24
    æĹĭ
    0.24
    è¦ģåģļåĪ°
    0.23
    æѦ
    0.23
    stones
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.