© 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. 20-TRANSCODER-HP
    7. 62827
    Prev
    Next
    INDEX
    Explanations

    scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    INES
    -0.27
     alloc
    -0.26
     queues
    -0.26
    illery
    -0.25
     pav
    -0.25
    æĬ¥è®°èĢħ
    -0.25
     deque
    -0.25
    ronym
    -0.25
    éħ¬
    -0.24
    reur
    -0.24
    POSITIVE LOGITS
    代表
    0.38
     representative
    0.35
     Representative
    0.30
    ä¼ļå½±åĵįåĪ°
    0.30
    æī©å±ķ
    0.28
    代表æĢ§
    0.28
    å½±åĵį
    0.28
    cit
    0.27
    转åĮĸ为
    0.27
     representing
    0.27
    Activations Density 73.454%

    No Known Activations