© 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. 88540
    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
    uner
    -0.31
    liqu
    -0.24
     umb
    -0.24
     sympathetic
    -0.23
    ä¸ĢäºĮ
    -0.23
     rising
    -0.23
     favourable
    -0.23
    /*/
    -0.22
    arlo
    -0.22
     subtraction
    -0.22
    POSITIVE LOGITS
    inded
    0.25
    绣
    0.23
    ienne
    0.23
    æĪijæĺ¯
    0.23
    atomy
    0.23
    çݯèĬĤ
    0.22
    æŁ¥çľĭåħ¨æĸĩ
    0.22
    urbed
    0.22
    elite
    0.22
    opsis
    0.22
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.