© 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. 130046
    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
    å¯IJ
    -0.27
     barg
    -0.25
     regarded
    -0.25
    æĿ¡è¯Ħ论
    -0.25
    ighter
    -0.24
     smoothed
    -0.24
    .sm
    -0.24
    (sm
    -0.24
    ?',
    -0.23
     enrolled
    -0.23
    POSITIVE LOGITS
    åıįè¿ĩæĿ¥
    0.26
    oss
    0.25
    rase
    0.25
    èµĦ
    0.25
    åıįä¹ĭ
    0.25
     плаÑģÑĤ
    0.24
     Dep
    0.23
     Port
    0.23
    jabi
    0.23
    asar
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.