© 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. 129052
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
    æ¯į
    -0.28
     completeness
    -0.27
    woke
    -0.27
    (norm
    -0.26
    atel
    -0.25
    麽
    -0.25
    mother
    -0.24
     mother
    -0.24
    adin
    -0.24
    èĢģå¦Ī
    -0.23
    POSITIVE LOGITS
    ien
    0.28
     Ø£Ùģ
    0.27
    iel
    0.26
     edi
    0.26
    edata
    0.26
    å®ŀè·µä¸Ń
    0.26
    пÑĥÑģка
    0.25
     Del
    0.25
    lett
    0.25
    ei
    0.25
    Activations Density 1.072%

    No Known Activations