© 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. 97632
    Prev
    Next
    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    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
    reso
    -0.27
    è¦ģåѦä¼ļ
    -0.27
    addir
    -0.26
    çĶļèĩ³è¿ĺ
    -0.26
     key
    -0.25
    ä»»ä½ķå½¢å¼ı
    -0.25
    ä¸įä»ħè¦ģ
    -0.25
    läss
    -0.25
     Dort
    -0.25
     chain
    -0.24
    POSITIVE LOGITS
    /tab
    0.27
    çļĦèĦļæŃ¥
    0.27
    麼
    0.25
    å¼¥
    0.25
    _inches
    0.24
    .asm
    0.24
    çļĦæľīæķĪ
    0.24
    “.
    0.23
    .nextElement
    0.23
     Griffin
    0.23
    Activations Density 0.032%

    No Known Activations