© 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. 97061
    Prev
    Next
    INDEX
    Explanations

    how

    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
     pat
    -0.27
    èķĥ
    -0.26
    æĭĸ
    -0.26
    åĢĴ
    -0.26
    All
    -0.25
    amazon
    -0.25
    æĸ¹å¼ıè¿Ľè¡Į
    -0.25
    对æĬĹ
    -0.24
    PAT
    -0.24
     grape
    -0.24
    POSITIVE LOGITS
    ordinary
    0.29
    -role
    0.27
    mis
    0.26
     handwriting
    0.26
    going
    0.26
     ordinary
    0.26
    acus
    0.25
    ÑģÑĤаÑĤ
    0.25
    igos
    0.25
    ãģijãĤĮãģ°
    0.25
    Activations Density 0.007%

    No Known Activations