© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97273
    Prev
    Next
    INDEX
    Explanations

    Programming and hardware concepts

    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
    Negative Logits
    idable
    -0.25
    èĹ©
    -0.25
    åĪ¶åº¦æĶ¹éĿ©
    -0.24
    italic
    -0.24
    .itemView
    -0.24
     {č↵č↵č↵
    -0.23
    å¹ķ
    -0.23
    妾
    -0.23
     {↵↵↵
    -0.23
    ä¸įåĪ°
    -0.23
    POSITIVE LOGITS
    楼ä¸ĭ
    0.24
    _shell
    0.24
    fits
    0.24
    Bus
    0.24
    ÑĮÑı
    0.24
    SRC
    0.23
    çģµ
    0.23
    search
    0.23
    NES
    0.23
    Src
    0.23
    Activations Density 0.004%

    No Known Activations