© 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. 129006
    Prev
    Next
    INDEX
    Explanations

    Fred

    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
    å¤§åľ°
    -0.28
    .caption
    -0.28
    jo
    -0.26
     gathering
    -0.25
    iss
    -0.24
    _formats
    -0.24
    å¨ĥ
    -0.24
    Spaces
    -0.24
    èľľ
    -0.24
    è¶ħè¶Ĭ
    -0.24
    POSITIVE LOGITS
    çĪ±äºº
    0.27
     theirs
    0.27
    hibit
    0.26
    ä»Ĭ天çļĦ
    0.26
    ä¸ŃåĽ½æ±½è½¦
    0.25
    积æŀģæĢ§
    0.25
    swick
    0.25
    utow
    0.25
    icut
    0.24
    etAddress
    0.24
    Activations Density 0.015%

    No Known Activations