© 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. 112935
    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
    Negative Logits
    ä¸Ĭä¸ĭ
    -0.27
    çĽĽå¤§
    -0.25
    ENTA
    -0.25
    ä¼ģ
    -0.25
    æŃ£å¥½
    -0.24
    æģ°å¥½
    -0.24
     пÑĥ
    -0.23
    PUT
    -0.22
    ATORY
    -0.22
    forc
    -0.22
    POSITIVE LOGITS
    SF
    0.25
    -handed
    0.25
    0.25
    æŶæķĪ
    0.24
     perme
    0.24
    ç¢
    0.23
     Del
    0.23
    iso
    0.23
     Zimmer
    0.23
    ä»ĺãģij
    0.22
    Activations Density 0.012%

    No Known Activations