© 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. 88091
    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
     ffi
    -0.26
    èµĦæľ¬
    -0.25
     Semester
    -0.23
    rão
    -0.23
    æ¯Ĵç´ł
    -0.22
    æĿ¿
    -0.22
     autob
    -0.22
    >{@
    -0.22
    ÅĤa
    -0.22
    顶
    -0.22
    POSITIVE LOGITS
    hib
    0.29
    plain
    0.28
    urve
    0.27
     Mish
    0.26
     Old
    0.24
    unks
    0.24
    ä¸Ģå¦Ĥ
    0.23
    æĪijä¸Ģ缴
    0.23
    iac
    0.23
    friend
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.